coreml

package
v0.8.0 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Jun 19, 2026 License: MIT Imports: 11 Imported by: 0

Documentation

Rendered for darwin/amd64

Overview

Package coreml provides purego-based Go bindings for the macOS CoreML framework.

Apple documentation: https://developer.apple.com/documentation/coreml

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func MLAllComputeDevices

func MLAllComputeDevices() *foundation.NSArray[MLComputeDeviceProtocol]

@abstract Returns an array containing all compute devices. @discussion The returned array contains all compute devices that are accessible. If a compute device becomes inaccessible for some reason (for e.g. if an external GPU is unplugged) then the subsequent call to`MLAllComputeDevices` will return an array without the compute device.

func MLComputePlanLoadContentsOfURLConfigurationCompletionHandler

func MLComputePlanLoadContentsOfURLConfigurationCompletionHandler(url *foundation.NSURL, configuration *MLModelConfiguration, handler func(*MLComputePlan, unsafe.Pointer))

Construct the compute plan of a model asynchronously given the location of its on-disk representation. @param url The location of its on-disk representation (.mlmodelc directory). @param configuration The model configuration. @param handler When the compute plan is constructed successfully or unsuccessfully, the completion handler is invoked with a valid MLComputePlan instance or NSError object.

func MLComputePlanLoadModelAssetConfigurationCompletionHandler

func MLComputePlanLoadModelAssetConfigurationCompletionHandler(asset *MLModelAsset, configuration *MLModelConfiguration, handler func(*MLComputePlan, unsafe.Pointer))

Construct the compute plan of a model asynchronously given the model asset. @param asset The model asset. @param configuration The model configuration. @param handler When the compute plan is constructed successfully or unsuccessfully, the completion handler is invoked with a valid MLComputePlan instance or NSError object.

func MLFeatureValueImageOptionCropAndScale

func MLFeatureValueImageOptionCropAndScale() *foundation.NSString

Key for VNImageCropAndScaleOption describing how to crop and scale the image (or region of interest) to the desired size

func MLFeatureValueImageOptionCropRect

func MLFeatureValueImageOptionCropRect() *foundation.NSString

Key for CGRect describing a crop region of interest of image source in normalized coordinates

func MLModelAuthorKey

func MLModelAuthorKey() *foundation.NSString

The author of this model

func MLModelAvailableComputeDevices

func MLModelAvailableComputeDevices() *foundation.NSArray[MLComputeDeviceProtocol]

func MLModelCompileModelAtURLCompletionHandler

func MLModelCompileModelAtURLCompletionHandler(modelURL *foundation.NSURL, handler func(*foundation.NSURL, unsafe.Pointer))

func MLModelCompileModelAtURLError

func MLModelCompileModelAtURLError(modelURL *foundation.NSURL) (*foundation.NSURL, error)

Compile a .mlmodel for this device @param modelURL URL file path to .mlmodel file you wish to compile @param error Any errors are surfaced here @returns a URL to the compiled .mlmodelc directory if successful The model is compiled to a temporary location on disk You must move the compiled model to a permanent location if you wish to keep it @discussion The returned model can be loaded using: @code [MLModel modelWithContentsOfURL:error:] @endcode

func MLModelCreatorDefinedKey

func MLModelCreatorDefinedKey() *foundation.NSString

Any additional pertinent information specified by the model creator

func MLModelDescriptionKey

func MLModelDescriptionKey() *foundation.NSString

A short description of what the model does and/or its purpose

func MLModelErrorDomain

func MLModelErrorDomain() uintptr

func MLModelLicenseKey

func MLModelLicenseKey() *foundation.NSString

License information for the model

func MLModelLoadContentsOfURLConfigurationCompletionHandler

func MLModelLoadContentsOfURLConfigurationCompletionHandler(url *foundation.NSURL, configuration *MLModelConfiguration, handler func(*MLModel, unsafe.Pointer))

Construct a model asynchronously given the location of its on-disk representation and configuration. Model loading may take time when the model content is not immediately available (e.g. encrypted model). Use this factory method especially when the caller is on the main thread. @param url the location of its on-disk representation (.mlmodelc directory). @param configuration The model configuration @param handler When the model load completes successfully or unsuccessfully, the completion handler is invoked with a valid MLModel instance or NSError object.

func MLModelLoadModelAssetConfigurationCompletionHandler

func MLModelLoadModelAssetConfigurationCompletionHandler(asset *MLModelAsset, configuration *MLModelConfiguration, handler func(*MLModel, unsafe.Pointer))

Construct a model asynchronously from a compiled model asset. @param asset Compiled model asset derived from in-memory or on-disk Core ML model @param configuration Model configuration that hold options for loading a model @param handler When the model load completes successfully or unsuccessfully, the completion handler is invoked with a valid MLModel instance or NSError object.

func MLModelStructureLoadContentsOfURLCompletionHandler

func MLModelStructureLoadContentsOfURLCompletionHandler(url *foundation.NSURL, handler func(*MLModelStructure, unsafe.Pointer))

Construct the model structure asynchronously given the location of its on-disk representation. @param url The location of its on-disk representation (.mlmodelc directory). @param handler When the model structure is constructed successfully or unsuccessfully, the completion handler is invoked with a valid MLModelStructure instance or NSError object.

func MLModelStructureLoadModelAssetCompletionHandler

func MLModelStructureLoadModelAssetCompletionHandler(asset *MLModelAsset, handler func(*MLModelStructure, unsafe.Pointer))

Construct the model structure asynchronously given the model asset. @param asset The model asset. @param handler When the model structure is constructed successfully or unsuccessfully, the completion handler is invoked with a valid MLModelStructure instance or NSError object.

func MLModelVersionStringKey

func MLModelVersionStringKey() *foundation.NSString

A version number encoded as a string

func SymbolAvailable

func SymbolAvailable(symbol string) bool

SymbolAvailable reports whether the named C symbol was bound when the library loaded. Calling a generated wrapper whose symbol is unavailable dereferences a nil function variable and panics.

Types

type Acl_entry_id_t

type Acl_entry_id_t int64
const (
	ACL_FIRST_ENTRY Acl_entry_id_t = 0
	ACL_NEXT_ENTRY  Acl_entry_id_t = -1
	ACL_LAST_ENTRY  Acl_entry_id_t = -2
)

func (Acl_entry_id_t) String

func (e Acl_entry_id_t) String() string

type Acl_flag_t

type Acl_flag_t int64
const (
	ACL_FLAG_DEFER_INHERIT      Acl_flag_t = 1
	ACL_FLAG_NO_INHERIT         Acl_flag_t = 131072
	ACL_ENTRY_INHERITED         Acl_flag_t = 16
	ACL_ENTRY_FILE_INHERIT      Acl_flag_t = 32
	ACL_ENTRY_DIRECTORY_INHERIT Acl_flag_t = 64
	ACL_ENTRY_LIMIT_INHERIT     Acl_flag_t = 128
	ACL_ENTRY_ONLY_INHERIT      Acl_flag_t = 256
)

func (Acl_flag_t) String

func (e Acl_flag_t) String() string

type Acl_perm_t

type Acl_perm_t int64
const (
	ACL_READ_DATA           Acl_perm_t = 2
	ACL_LIST_DIRECTORY      Acl_perm_t = 2
	ACL_WRITE_DATA          Acl_perm_t = 4
	ACL_ADD_FILE            Acl_perm_t = 4
	ACL_EXECUTE             Acl_perm_t = 8
	ACL_SEARCH              Acl_perm_t = 8
	ACL_DELETE              Acl_perm_t = 16
	ACL_APPEND_DATA         Acl_perm_t = 32
	ACL_ADD_SUBDIRECTORY    Acl_perm_t = 32
	ACL_DELETE_CHILD        Acl_perm_t = 64
	ACL_READ_ATTRIBUTES     Acl_perm_t = 128
	ACL_WRITE_ATTRIBUTES    Acl_perm_t = 256
	ACL_READ_EXTATTRIBUTES  Acl_perm_t = 512
	ACL_WRITE_EXTATTRIBUTES Acl_perm_t = 1024
	ACL_READ_SECURITY       Acl_perm_t = 2048
	ACL_WRITE_SECURITY      Acl_perm_t = 4096
	ACL_CHANGE_OWNER        Acl_perm_t = 8192
	ACL_SYNCHRONIZE         Acl_perm_t = 1048576
)

func (Acl_perm_t) String

func (e Acl_perm_t) String() string

type Acl_tag_t

type Acl_tag_t int64
const (
	ACL_UNDEFINED_TAG  Acl_tag_t = 0
	ACL_EXTENDED_ALLOW Acl_tag_t = 1
	ACL_EXTENDED_DENY  Acl_tag_t = 2
)

func (Acl_tag_t) String

func (e Acl_tag_t) String() string

type Acl_type_t

type Acl_type_t int64
const (
	ACL_TYPE_EXTENDED Acl_type_t = 256
	ACL_TYPE_ACCESS   Acl_type_t = 0
	ACL_TYPE_DEFAULT  Acl_type_t = 1
	ACL_TYPE_AFS      Acl_type_t = 2
	ACL_TYPE_CODA     Acl_type_t = 3
	ACL_TYPE_NTFS     Acl_type_t = 4
	ACL_TYPE_NWFS     Acl_type_t = 5
)

func (Acl_type_t) String

func (e Acl_type_t) String() string

type Clockid_t

type Clockid_t int64

func (Clockid_t) String

func (e Clockid_t) String() string

type Dispatch_autorelease_frequency_t

type Dispatch_autorelease_frequency_t uint64
const (
	DISPATCH_AUTORELEASE_FREQUENCY_INHERIT   Dispatch_autorelease_frequency_t = 0
	DISPATCH_AUTORELEASE_FREQUENCY_WORK_ITEM Dispatch_autorelease_frequency_t = 1
	DISPATCH_AUTORELEASE_FREQUENCY_NEVER     Dispatch_autorelease_frequency_t = 2
)

func (Dispatch_autorelease_frequency_t) String

type Dispatch_block_flags_t

type Dispatch_block_flags_t uint64
const (
	DISPATCH_BLOCK_BARRIER           Dispatch_block_flags_t = 1
	DISPATCH_BLOCK_DETACHED          Dispatch_block_flags_t = 2
	DISPATCH_BLOCK_ASSIGN_CURRENT    Dispatch_block_flags_t = 4
	DISPATCH_BLOCK_NO_QOS_CLASS      Dispatch_block_flags_t = 8
	DISPATCH_BLOCK_INHERIT_QOS_CLASS Dispatch_block_flags_t = 16
	DISPATCH_BLOCK_ENFORCE_QOS_CLASS Dispatch_block_flags_t = 32
)

func (Dispatch_block_flags_t) String

func (e Dispatch_block_flags_t) String() string

type EvCmd

type EvCmd int64
const (
	EVNOP   EvCmd = 0
	EVHIDE  EvCmd = 1
	EVSHOW  EvCmd = 2
	EVMOVE  EvCmd = 3
	EVLEVEL EvCmd = 4
)

func (EvCmd) String

func (e EvCmd) String() string

type Filesec_property_t

type Filesec_property_t int64
const (
	FILESEC_OWNER         Filesec_property_t = 1
	FILESEC_GROUP         Filesec_property_t = 2
	FILESEC_UUID          Filesec_property_t = 3
	FILESEC_MODE          Filesec_property_t = 4
	FILESEC_ACL           Filesec_property_t = 5
	FILESEC_GRPUUID       Filesec_property_t = 6
	FILESEC_ACL_RAW       Filesec_property_t = 100
	FILESEC_ACL_ALLOCSIZE Filesec_property_t = 101
)

func (Filesec_property_t) String

func (e Filesec_property_t) String() string

type Idtype_t

type Idtype_t int64
const (
	P_ALL  Idtype_t = 0
	P_PID  Idtype_t = 1
	P_PGID Idtype_t = 2
)

func (Idtype_t) String

func (e Idtype_t) String() string

type Ipc_info_object_type_t

type Ipc_info_object_type_t int64
const (
	IPC_OTYPE_NONE                 Ipc_info_object_type_t = 0
	IPC_OTYPE_THREAD_CONTROL       Ipc_info_object_type_t = 1
	IPC_OTYPE_TASK_CONTROL         Ipc_info_object_type_t = 2
	IPC_OTYPE_HOST                 Ipc_info_object_type_t = 3
	IPC_OTYPE_HOST_PRIV            Ipc_info_object_type_t = 4
	IPC_OTYPE_PROCESSOR            Ipc_info_object_type_t = 5
	IPC_OTYPE_PROCESSOR_SET        Ipc_info_object_type_t = 6
	IPC_OTYPE_PROCESSOR_SET_NAME   Ipc_info_object_type_t = 7
	IPC_OTYPE_TIMER                Ipc_info_object_type_t = 8
	IPC_OTYPE_PORT_SUBST_ONCE      Ipc_info_object_type_t = 9
	IPC_OTYPE_MIG                  Ipc_info_object_type_t = 10
	IPC_OTYPE_MEMORY_OBJECT        Ipc_info_object_type_t = 11
	IPC_OTYPE_XMM_PAGER            Ipc_info_object_type_t = 12
	IPC_OTYPE_XMM_KERNEL           Ipc_info_object_type_t = 13
	IPC_OTYPE_XMM_REPLY            Ipc_info_object_type_t = 14
	IPC_OTYPE_UND_REPLY            Ipc_info_object_type_t = 15
	IPC_OTYPE_HOST_NOTIFY          Ipc_info_object_type_t = 16
	IPC_OTYPE_HOST_SECURITY        Ipc_info_object_type_t = 17
	IPC_OTYPE_LEDGER               Ipc_info_object_type_t = 18
	IPC_OTYPE_MAIN_DEVICE          Ipc_info_object_type_t = 19
	IPC_OTYPE_TASK_NAME            Ipc_info_object_type_t = 20
	IPC_OTYPE_SUBSYSTEM            Ipc_info_object_type_t = 21
	IPC_OTYPE_IO_DONE_QUEUE        Ipc_info_object_type_t = 22
	IPC_OTYPE_SEMAPHORE            Ipc_info_object_type_t = 23
	IPC_OTYPE_LOCK_SET             Ipc_info_object_type_t = 24
	IPC_OTYPE_CLOCK                Ipc_info_object_type_t = 25
	IPC_OTYPE_CLOCK_CTRL           Ipc_info_object_type_t = 26
	IPC_OTYPE_IOKIT_IDENT          Ipc_info_object_type_t = 27
	IPC_OTYPE_NAMED_ENTRY          Ipc_info_object_type_t = 28
	IPC_OTYPE_IOKIT_CONNECT        Ipc_info_object_type_t = 29
	IPC_OTYPE_IOKIT_OBJECT         Ipc_info_object_type_t = 30
	IPC_OTYPE_UPL                  Ipc_info_object_type_t = 31
	IPC_OTYPE_MEM_OBJ_CONTROL      Ipc_info_object_type_t = 32
	IPC_OTYPE_AU_SESSIONPORT       Ipc_info_object_type_t = 33
	IPC_OTYPE_FILEPORT             Ipc_info_object_type_t = 34
	IPC_OTYPE_LABELH               Ipc_info_object_type_t = 35
	IPC_OTYPE_TASK_RESUME          Ipc_info_object_type_t = 36
	IPC_OTYPE_VOUCHER              Ipc_info_object_type_t = 37
	IPC_OTYPE_VOUCHER_ATTR_CONTROL Ipc_info_object_type_t = 38
	IPC_OTYPE_WORK_INTERVAL        Ipc_info_object_type_t = 39
	IPC_OTYPE_UX_HANDLER           Ipc_info_object_type_t = 40
	IPC_OTYPE_UEXT_OBJECT          Ipc_info_object_type_t = 41
	IPC_OTYPE_ARCADE_REG           Ipc_info_object_type_t = 42
	IPC_OTYPE_EVENTLINK            Ipc_info_object_type_t = 43
	IPC_OTYPE_TASK_INSPECT         Ipc_info_object_type_t = 44
	IPC_OTYPE_TASK_READ            Ipc_info_object_type_t = 45
	IPC_OTYPE_THREAD_INSPECT       Ipc_info_object_type_t = 46
	IPC_OTYPE_THREAD_READ          Ipc_info_object_type_t = 47
	IPC_OTYPE_SUID_CRED            Ipc_info_object_type_t = 48
	IPC_OTYPE_HYPERVISOR           Ipc_info_object_type_t = 49
	IPC_OTYPE_TASK_ID_TOKEN        Ipc_info_object_type_t = 50
	IPC_OTYPE_TASK_FATAL           Ipc_info_object_type_t = 51
	IPC_OTYPE_KCDATA               Ipc_info_object_type_t = 52
	IPC_OTYPE_EXCLAVES_RESOURCE    Ipc_info_object_type_t = 53
	IPC_OTYPE_THREAD_RESUME        Ipc_info_object_type_t = 54
	IPC_OTYPE_UNKNOWN              Ipc_info_object_type_t = 4294967295
)

func (Ipc_info_object_type_t) String

func (e Ipc_info_object_type_t) String() string

type Launch_data_type_t

type Launch_data_type_t int64
const (
	LAUNCH_DATA_DICTIONARY Launch_data_type_t = 1
	LAUNCH_DATA_ARRAY      Launch_data_type_t = 2
	LAUNCH_DATA_FD         Launch_data_type_t = 3
	LAUNCH_DATA_INTEGER    Launch_data_type_t = 4
	LAUNCH_DATA_REAL       Launch_data_type_t = 5
	LAUNCH_DATA_BOOL       Launch_data_type_t = 6
	LAUNCH_DATA_STRING     Launch_data_type_t = 7
	LAUNCH_DATA_OPAQUE     Launch_data_type_t = 8
	LAUNCH_DATA_ERRNO      Launch_data_type_t = 9
	LAUNCH_DATA_MACHPORT   Launch_data_type_t = 10
)

func (Launch_data_type_t) String

func (e Launch_data_type_t) String() string

type MDLabelDomain

type MDLabelDomain int64

@typedef MDLabelDomain @abstract These constants are used to specify a domain to MDLabelCreate().

const (
	KMDLabelUserDomain  MDLabelDomain = 0
	KMDLabelLocalDomain MDLabelDomain = 1
)

func (MDLabelDomain) String

func (e MDLabelDomain) String() string

type MDQueryOptionFlags

type MDQueryOptionFlags int64
const (
	KMDQuerySynchronous        MDQueryOptionFlags = 1
	KMDQueryWantsUpdates       MDQueryOptionFlags = 4
	KMDQueryAllowFSTranslation MDQueryOptionFlags = 8
)

func (MDQueryOptionFlags) String

func (e MDQueryOptionFlags) String() string

type MDQuerySortOptionFlags

type MDQuerySortOptionFlags int64

@enum MDQuerySortOptionFlags @constant kMDQueryReverseSortOrderFlag Sort the attribute in reverse order.

const (
	KMDQueryReverseSortOrderFlag MDQuerySortOptionFlags = 1
)

func (MDQuerySortOptionFlags) String

func (e MDQuerySortOptionFlags) String() string

type MLArrayBatchProvider

type MLArrayBatchProvider struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlarraybatchprovider

func MLArrayBatchProviderFromID

func MLArrayBatchProviderFromID(id objc.ID) *MLArrayBatchProvider

func (*MLArrayBatchProvider) Array

func (*MLArrayBatchProvider) InitWithDictionaryError

func (o *MLArrayBatchProvider) InitWithDictionaryError(dictionary *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLArrayBatchProvider, error)

Initialize with a dictionary which maps feature names to an array of values [String : [Any]] Error is returned if all arrays do not have equal length or if array values for a specific feature name do not have the same type or not expressible as MLFeatureValue

func (*MLArrayBatchProvider) InitWithFeatureProviderArray

func (o *MLArrayBatchProvider) InitWithFeatureProviderArray(array *foundation.NSArray[MLFeatureProvider]) *MLArrayBatchProvider

Initalize with an array of feature providers

type MLBatchProvider

type MLBatchProvider interface {
	FeaturesAtIndex(index int) MLFeatureProvider
	Count() int
}

MLBatchProvider wraps the ObjC protocol MLBatchProvider.

type MLCPUComputeDevice

type MLCPUComputeDevice struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlcpucomputedevice

func MLCPUComputeDeviceFromID

func MLCPUComputeDeviceFromID(id objc.ID) *MLCPUComputeDevice

type MLComputeDeviceProtocol

type MLComputeDeviceProtocol interface {
}

MLComputeDeviceProtocol wraps the ObjC protocol MLComputeDeviceProtocol.

type MLComputePlan

type MLComputePlan struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlcomputeplan

func MLComputePlanFromID

func MLComputePlanFromID(id objc.ID) *MLComputePlan

func (*MLComputePlan) ComputeDeviceUsageForMLProgramOperation

func (o *MLComputePlan) ComputeDeviceUsageForMLProgramOperation(operation *MLModelStructureProgramOperation) *MLComputePlanDeviceUsage

Returns The anticipated compute devices that would be used for executing an ML Program operation. @param operation An ML Program operation. @returns The anticipated compute devices that would be used for executing the operation or `nil`if the usage couldn't be determined.

func (*MLComputePlan) ComputeDeviceUsageForNeuralNetworkLayer

func (o *MLComputePlan) ComputeDeviceUsageForNeuralNetworkLayer(layer *MLModelStructureNeuralNetworkLayer) *MLComputePlanDeviceUsage

Returns the anticipated compute devices that would be used for executing a NeuralNetwork layer. @param layer A NeuralNetwork layer. @returns The anticipated compute devices that would be used for executing the layer or `nil` if the usage couldn't be determined.

func (*MLComputePlan) EstimatedCostOfMLProgramOperation

func (o *MLComputePlan) EstimatedCostOfMLProgramOperation(operation *MLModelStructureProgramOperation) *MLComputePlanCost

Returns the estimated cost of executing an ML Program operation. @param operation An ML Program operation. @returns The estimated cost of executing the operation or nil if the cost couldn't be estimated.

func (*MLComputePlan) ModelStructure

func (o *MLComputePlan) ModelStructure() *MLModelStructure

type MLComputePlanCost

type MLComputePlanCost struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlcomputeplancost

func MLComputePlanCostFromID

func MLComputePlanCostFromID(id objc.ID) *MLComputePlanCost

func (*MLComputePlanCost) Weight

func (o *MLComputePlanCost) Weight() float64

type MLComputePlanDeviceUsage

type MLComputePlanDeviceUsage struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlcomputeplandeviceusage

func MLComputePlanDeviceUsageFromID

func MLComputePlanDeviceUsageFromID(id objc.ID) *MLComputePlanDeviceUsage

func (*MLComputePlanDeviceUsage) PreferredComputeDevice

func (o *MLComputePlanDeviceUsage) PreferredComputeDevice() MLComputeDeviceProtocol

The compute device that the framework prefers to execute the layer/operation.

func (*MLComputePlanDeviceUsage) SupportedComputeDevices

func (o *MLComputePlanDeviceUsage) SupportedComputeDevices() *foundation.NSArray[MLComputeDeviceProtocol]

The compute devices that can execute the layer/operation.

type MLComputeUnits

type MLComputeUnits int64
const (
	MLComputeUnitsCPUOnly            MLComputeUnits = 0
	MLComputeUnitsCPUAndGPU          MLComputeUnits = 1
	MLComputeUnitsAll                MLComputeUnits = 2
	MLComputeUnitsCPUAndNeuralEngine MLComputeUnits = 3
)

func (MLComputeUnits) String

func (e MLComputeUnits) String() string

type MLCustomLayer

type MLCustomLayer interface {
	InitWithParameterDictionaryError(parameters *foundation.NSDictionary[*foundation.NSString, objc.ID]) (unsafe.Pointer, error)
	SetWeightDataError(weights *foundation.NSArray[*foundation.NSData]) (bool, error)
	OutputShapesForInputShapesError(inputShapes *foundation.NSArray[objc.ID]) (*foundation.NSArray[objc.ID], error)
	EvaluateOnCPUWithInputsOutputsError(inputs *foundation.NSArray[*MLMultiArray], outputs *foundation.NSArray[*MLMultiArray]) (bool, error)
}

MLCustomLayer wraps the ObjC protocol MLCustomLayer.

type MLCustomModel

type MLCustomModel interface {
	InitWithModelDescriptionParameterDictionaryError(modelDescription *MLModelDescription, parameters *foundation.NSDictionary[*foundation.NSString, objc.ID]) (unsafe.Pointer, error)
	PredictionFromFeaturesOptionsError(input MLFeatureProvider, options *MLPredictionOptions) (MLFeatureProvider, error)
}

MLCustomModel wraps the ObjC protocol MLCustomModel.

type MLDictionaryConstraint

type MLDictionaryConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mldictionaryconstraint

func MLDictionaryConstraintFromID

func MLDictionaryConstraintFromID(id objc.ID) *MLDictionaryConstraint

func (*MLDictionaryConstraint) KeyType

type MLDictionaryFeatureProvider

type MLDictionaryFeatureProvider struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mldictionaryfeatureprovider

func MLDictionaryFeatureProviderFromID

func MLDictionaryFeatureProviderFromID(id objc.ID) *MLDictionaryFeatureProvider

func (*MLDictionaryFeatureProvider) Dictionary

Dictionary holding the feature values

func (*MLDictionaryFeatureProvider) InitWithDictionaryError

Create from a generic dictionary by converting all values to MLFeatureValues or from a dictionary with values already stored as MLFeatureValues. An error results if the values are not or cannot be represented as MLFeatureValues.

func (*MLDictionaryFeatureProvider) ObjectForKeyedSubscript

func (o *MLDictionaryFeatureProvider) ObjectForKeyedSubscript(featureName *foundation.NSString) *MLFeatureValue

Get the value for specified feature

type MLFeatureDescription

type MLFeatureDescription struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlfeaturedescription

func MLFeatureDescriptionFromID

func MLFeatureDescriptionFromID(id objc.ID) *MLFeatureDescription

func (*MLFeatureDescription) DictionaryConstraint

func (o *MLFeatureDescription) DictionaryConstraint() *MLDictionaryConstraint

Constraint when type == MLFeatureTypeDictionary, nil otherwise

func (*MLFeatureDescription) ImageConstraint

func (o *MLFeatureDescription) ImageConstraint() *MLImageConstraint

Constraint when type == MLFeatureTypeImage, nil otherwise

func (*MLFeatureDescription) IsAllowedValue

func (o *MLFeatureDescription) IsAllowedValue(value *MLFeatureValue) bool

Check if MLFeatureValue is valid based on this description

func (*MLFeatureDescription) IsOptional

func (o *MLFeatureDescription) IsOptional() bool

Whether this feature can take an undefined value or not

func (*MLFeatureDescription) MultiArrayConstraint

func (o *MLFeatureDescription) MultiArrayConstraint() *MLMultiArrayConstraint

Constraint when type == MLFeatureTypeMultiArray, nil otherwise

func (*MLFeatureDescription) Name

Name of feature

func (*MLFeatureDescription) SequenceConstraint

func (o *MLFeatureDescription) SequenceConstraint() *MLSequenceConstraint

Constraint when type == MLFeatureTypeSequence, nil otherwise

func (*MLFeatureDescription) StateConstraint

func (o *MLFeatureDescription) StateConstraint() *MLStateConstraint

The state feature value constraint. The property has a value when `.type == MLFeatureTypeState`.

func (*MLFeatureDescription) Type

Type of data

type MLFeatureProvider

type MLFeatureProvider interface {
}

MLFeatureProvider wraps the ObjC protocol MLFeatureProvider.

type MLFeatureType

type MLFeatureType int64
const (
	MLFeatureTypeInvalid MLFeatureType = 0
	// Discrete values, sometimes used to hold numeric encoding of a categorical value
	MLFeatureTypeInt64 MLFeatureType = 1
	// Continuous values
	MLFeatureTypeDouble MLFeatureType = 2
	MLFeatureTypeString MLFeatureType = 3
	// CVPixelBufferRef
	MLFeatureTypeImage MLFeatureType = 4
	// MLMultiArray
	MLFeatureTypeMultiArray MLFeatureType = 5
	// Numerically weighted hashable objects (e.g. word counts)
	MLFeatureTypeDictionary MLFeatureType = 6
	// MLSequence. Ordered collection of feature values with the same type
	MLFeatureTypeSequence MLFeatureType = 7
	// MLState. Represents a model state that may be updated in each inference.
	MLFeatureTypeState MLFeatureType = 8
)

func (MLFeatureType) String

func (e MLFeatureType) String() string

type MLFeatureValue

type MLFeatureValue struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlfeaturevalue

func MLFeatureValueFeatureValueWithCGImageConstraintOptionsError

func MLFeatureValueFeatureValueWithCGImageConstraintOptionsError(cgImage unsafe.Pointer, constraint *MLImageConstraint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from CGImage, using the size and type information required by feature description (orientation is assumed to be kCGImagePropertyOrientationUp)

func MLFeatureValueFeatureValueWithCGImageOrientationConstraintOptionsError

func MLFeatureValueFeatureValueWithCGImageOrientationConstraintOptionsError(cgImage unsafe.Pointer, orientation imageio.CGImagePropertyOrientation, constraint *MLImageConstraint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from CGImage w/ specified orientation, using the size and type information required by feature description

func MLFeatureValueFeatureValueWithCGImageOrientationPixelsWidePixelsHighPixelFormatTypeOptionsError

func MLFeatureValueFeatureValueWithCGImageOrientationPixelsWidePixelsHighPixelFormatTypeOptionsError(cgImage unsafe.Pointer, orientation imageio.CGImagePropertyOrientation, pixelsWide int, pixelsHigh int, pixelFormatType uint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from CGImage w/ specified orientation

func MLFeatureValueFeatureValueWithCGImagePixelsWidePixelsHighPixelFormatTypeOptionsError

func MLFeatureValueFeatureValueWithCGImagePixelsWidePixelsHighPixelFormatTypeOptionsError(cgImage unsafe.Pointer, pixelsWide int, pixelsHigh int, pixelFormatType uint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from CGImage (orientation is assumed to be kCGImagePropertyOrientationUp)

func MLFeatureValueFeatureValueWithDictionaryError

func MLFeatureValueFeatureValueWithDictionaryError(value *foundation.NSDictionary[objc.ID, *foundation.NSNumber]) (*MLFeatureValue, error)

For encoding a sparse feature set or for encoding probabilities. Input keys that are not NSNumber * or NSString * are rejected on construction and return a MLModelErrorFeatureTypeMismatch error. Further validation for consistency occurs on evaluation

func MLFeatureValueFeatureValueWithDouble

func MLFeatureValueFeatureValueWithDouble(value float64) *MLFeatureValue

func MLFeatureValueFeatureValueWithImageAtURLConstraintOptionsError

func MLFeatureValueFeatureValueWithImageAtURLConstraintOptionsError(url *foundation.NSURL, constraint *MLImageConstraint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from an image on disk, using a model specified image constraint. Orientation is read from Exif if avaiable

func MLFeatureValueFeatureValueWithImageAtURLOrientationConstraintOptionsError

func MLFeatureValueFeatureValueWithImageAtURLOrientationConstraintOptionsError(url *foundation.NSURL, orientation imageio.CGImagePropertyOrientation, constraint *MLImageConstraint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from an image on disk using a model specified image constraint. The passed in orientation supersedes any in the file

func MLFeatureValueFeatureValueWithImageAtURLOrientationPixelsWidePixelsHighPixelFormatTypeOptionsError

func MLFeatureValueFeatureValueWithImageAtURLOrientationPixelsWidePixelsHighPixelFormatTypeOptionsError(url *foundation.NSURL, orientation imageio.CGImagePropertyOrientation, pixelsWide int, pixelsHigh int, pixelFormatType uint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from an image on disk. The passed in orientation supersedes any in the file

func MLFeatureValueFeatureValueWithImageAtURLPixelsWidePixelsHighPixelFormatTypeOptionsError

func MLFeatureValueFeatureValueWithImageAtURLPixelsWidePixelsHighPixelFormatTypeOptionsError(url *foundation.NSURL, pixelsWide int, pixelsHigh int, pixelFormatType uint, options *foundation.NSDictionary[*foundation.NSString, objc.ID]) (*MLFeatureValue, error)

Construct image feature value from an image on disk. Orientation is read from Exif if avaiable

func MLFeatureValueFeatureValueWithInt64

func MLFeatureValueFeatureValueWithInt64(value int64) *MLFeatureValue

Hold an object with the specified value

func MLFeatureValueFeatureValueWithMultiArray

func MLFeatureValueFeatureValueWithMultiArray(value *MLMultiArray) *MLFeatureValue

func MLFeatureValueFeatureValueWithPixelBuffer

func MLFeatureValueFeatureValueWithPixelBuffer(value unsafe.Pointer) *MLFeatureValue

func MLFeatureValueFeatureValueWithSequence

func MLFeatureValueFeatureValueWithSequence(sequence *MLSequence) *MLFeatureValue

func MLFeatureValueFeatureValueWithString

func MLFeatureValueFeatureValueWithString(value *foundation.NSString) *MLFeatureValue

func MLFeatureValueFromID

func MLFeatureValueFromID(id objc.ID) *MLFeatureValue

func MLFeatureValueUndefinedFeatureValueWithType

func MLFeatureValueUndefinedFeatureValueWithType(type_ MLFeatureType) *MLFeatureValue

Represent an undefined value of a specified type

func (*MLFeatureValue) DictionaryValue

func (o *MLFeatureValue) DictionaryValue() *foundation.NSDictionary[objc.ID, *foundation.NSNumber]

Populated value if the type is MLFeatureTypeDictionary

func (*MLFeatureValue) DoubleValue

func (o *MLFeatureValue) DoubleValue() float64

Populated value if the type is MLFeatureTypeDouble

func (*MLFeatureValue) ImageBufferValue

func (o *MLFeatureValue) ImageBufferValue() unsafe.Pointer

Populated value if the type is MLFeatureTypeImage

func (*MLFeatureValue) Int64Value

func (o *MLFeatureValue) Int64Value() int64

Populated value if the type is MLFeatureTypeInt64

func (*MLFeatureValue) IsEqualToFeatureValue

func (o *MLFeatureValue) IsEqualToFeatureValue(value *MLFeatureValue) bool

@abstract Returns a Boolean value that indicates whether a feature value is equal to another. @discussion If the types of the MLFeatureValue objects "self" and "value" are integer in one case and double in the other (in either order) then those mixed mode numeric values are compared as NSNumbers. Otherwise if the types of the MLFeatureValue objects are different NO is returned. When "self" and "value" are both PixelBuffer MLFeatureValue types, only their CVPixelBufferRef values are compared for equality, the underlying arrays of pixelValues are not examined. [So, distinct PixelBuffer MLFeatureValue objects with distinct CVPixelBufferRef values which encapsulate the same array of pixels will compare *not* equal.] For all other (matching) MLFeatureValue types, the BOOL value returned is the result of comparing "self" with "value" via isEqualToNumber:, isEqualToString:, isEqualtoDictionary:, isEqualToMultiArray:, isEqualToArray: as chosen by the MLFeatureValue types.

func (*MLFeatureValue) IsUndefined

func (o *MLFeatureValue) IsUndefined() bool

True if the value represents a missing or undefined value

func (*MLFeatureValue) MultiArrayValue

func (o *MLFeatureValue) MultiArrayValue() *MLMultiArray

Populated value if the type is MLFeatureTypeMultiArray

func (*MLFeatureValue) SequenceValue

func (o *MLFeatureValue) SequenceValue() *MLSequence

Populated value if the type is MLFeatureTypeSequence

func (*MLFeatureValue) StringValue

func (o *MLFeatureValue) StringValue() *foundation.NSString

Populated value if the type is MLFeatureTypeString

func (*MLFeatureValue) Type

func (o *MLFeatureValue) Type() MLFeatureType

Type of the value for which the corresponding property below is held

type MLGPUComputeDevice

type MLGPUComputeDevice struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlgpucomputedevice

func MLGPUComputeDeviceFromID

func MLGPUComputeDeviceFromID(id objc.ID) *MLGPUComputeDevice

func (*MLGPUComputeDevice) MetalDevice

func (o *MLGPUComputeDevice) MetalDevice() metal.MTLDevice

type MLImageConstraint

type MLImageConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlimageconstraint

func MLImageConstraintFromID

func MLImageConstraintFromID(id objc.ID) *MLImageConstraint

func (*MLImageConstraint) PixelFormatType

func (o *MLImageConstraint) PixelFormatType() uint

The accepted kCVPixelFormatType for the image.

func (*MLImageConstraint) PixelsHigh

func (o *MLImageConstraint) PixelsHigh() int

The required or default height of the image

func (*MLImageConstraint) PixelsWide

func (o *MLImageConstraint) PixelsWide() int

The required or default width of the image

func (*MLImageConstraint) SizeConstraint

func (o *MLImageConstraint) SizeConstraint() *MLImageSizeConstraint

Detailed image size constraint

type MLImageSize

type MLImageSize struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlimagesize

func MLImageSizeFromID

func MLImageSizeFromID(id objc.ID) *MLImageSize

func (*MLImageSize) PixelsHigh

func (o *MLImageSize) PixelsHigh() int

func (*MLImageSize) PixelsWide

func (o *MLImageSize) PixelsWide() int

type MLImageSizeConstraint

type MLImageSizeConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlimagesizeconstraint

func MLImageSizeConstraintFromID

func MLImageSizeConstraintFromID(id objc.ID) *MLImageSizeConstraint

func (*MLImageSizeConstraint) EnumeratedImageSizes

func (o *MLImageSizeConstraint) EnumeratedImageSizes() *foundation.NSArray[*MLImageSize]

func (*MLImageSizeConstraint) PixelsHighRange

func (o *MLImageSizeConstraint) PixelsHighRange() foundation.NSRange

func (*MLImageSizeConstraint) PixelsWideRange

func (o *MLImageSizeConstraint) PixelsWideRange() foundation.NSRange

func (*MLImageSizeConstraint) Type

type MLImageSizeConstraintType

type MLImageSizeConstraintType int64
const (
	MLImageSizeConstraintTypeUnspecified MLImageSizeConstraintType = 0
	MLImageSizeConstraintTypeEnumerated  MLImageSizeConstraintType = 2
	MLImageSizeConstraintTypeRange       MLImageSizeConstraintType = 3
)

func (MLImageSizeConstraintType) String

func (e MLImageSizeConstraintType) String() string

type MLKey

type MLKey struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlkey

func MLKeyFromID

func MLKeyFromID(id objc.ID) *MLKey

func (*MLKey) Name

func (o *MLKey) Name() *foundation.NSString

func (*MLKey) Scope

func (o *MLKey) Scope() *foundation.NSString

type MLMetricKey

type MLMetricKey struct {
	MLKey
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmetrickey

func MLMetricKeyEpochIndex

func MLMetricKeyEpochIndex() *MLMetricKey

func MLMetricKeyFromID

func MLMetricKeyFromID(id objc.ID) *MLMetricKey

func MLMetricKeyLossValue

func MLMetricKeyLossValue() *MLMetricKey

func MLMetricKeyMiniBatchIndex

func MLMetricKeyMiniBatchIndex() *MLMetricKey

type MLModel

type MLModel struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodel

func MLModelFromID

func MLModelFromID(id objc.ID) *MLModel

func MLModelModelWithContentsOfURLConfigurationError

func MLModelModelWithContentsOfURLConfigurationError(url *foundation.NSURL, configuration *MLModelConfiguration) (*MLModel, error)

Construct a model given the location of its on-disk representation. Returns nil on error.

func MLModelModelWithContentsOfURLError

func MLModelModelWithContentsOfURLError(url *foundation.NSURL) (*MLModel, error)

Construct a model with a default MLModelConfiguration object

func (*MLModel) Configuration

func (o *MLModel) Configuration() *MLModelConfiguration

The load-time parameters used to instantiate this MLModel object.

func (*MLModel) ModelDescription

func (o *MLModel) ModelDescription() *MLModelDescription

A model holds a description of its required inputs and expected outputs.

func (*MLModel) NewState

func (o *MLModel) NewState() *MLState

Creates a new state object. Core ML framework will allocate the state buffers declared in the model. The allocated state buffers are initialized to zeros. To initialize with different values, use `.withMultiArray(for:)` to get the mutable `MLMultiArray`-view to the state buffer. It returns an empty state when the model is stateless. One can use the empty state with stateful prediction functions such as `prediction(from:using:)` and those predictions will be stateless. This simplifies the call site which may or may not use a stateful model. ```swift // Create state that contains two state buffers: s1 and s2. // Then, initialize s1 to 1.0 and s2 to 2.0. let state = model.newState() state.withMultiArray(for: "s1") { stateMultiArray in stateMultiArray[0] = 1.0 } state.withMultiArray(for: "s2") { stateMultiArray in stateMultiArray[0] = 2.0 } ```

func (*MLModel) ParameterValueForKeyError

func (o *MLModel) ParameterValueForKeyError(key *MLParameterKey) (objc.ID, error)

Provides value for the given parameter. Returns nil on error.

func (*MLModel) PredictionFromFeaturesCompletionHandler

func (o *MLModel) PredictionFromFeaturesCompletionHandler(input MLFeatureProvider, completionHandler func(objc.ID, unsafe.Pointer))

Run a prediction on a model asynchronously. This is a convenience overload method of `prediction(from:options:) async` that uses the default prediction options. - Parameters - input: The input features to make a prediction from. - completionHandler: A block that will be invoked once the prediction has completed successfully or unsuccessfully. On success, it is invoked with a valid model output. On failure, it is invoked with a nil output and NSError

func (*MLModel) PredictionFromFeaturesError

func (o *MLModel) PredictionFromFeaturesError(input MLFeatureProvider) (MLFeatureProvider, error)

Run a prediction on a model synchronously. This is a convenience overload method of `prediction(from:options:)` that uses the default prediction options. - Parameters - input: The input features to make a prediction from. - error: The output parameter to be filled with error information on failure. - Returns: The output features from the prediction.

func (*MLModel) PredictionFromFeaturesOptionsCompletionHandler

func (o *MLModel) PredictionFromFeaturesOptionsCompletionHandler(input MLFeatureProvider, options *MLPredictionOptions, completionHandler func(objc.ID, unsafe.Pointer))

Run a prediction on a model asynchronously. - Parameters - input: The input features to make a prediction from. - options: Prediction options to modify how the prediction is run. - completionHandler: A block that will be invoked once the prediction has completed successfully or unsuccessfully. On success, it is invoked with a valid model output. On failure, it is invoked with a nil output and NSError

func (*MLModel) PredictionFromFeaturesOptionsError

func (o *MLModel) PredictionFromFeaturesOptionsError(input MLFeatureProvider, options *MLPredictionOptions) (MLFeatureProvider, error)

Run a prediction on a model synchronously - Parameters - input: The input features to make a prediction from. - options: Prediction options to modify how the prediction is run. - error: The output parameter to be filled with error information on failure. - Returns: The output features from the prediction.

func (*MLModel) PredictionFromFeaturesUsingStateError

func (o *MLModel) PredictionFromFeaturesUsingStateError(inputFeatures MLFeatureProvider, state *MLState) (MLFeatureProvider, error)

Run a stateful prediction synchronously. Use this method to run predictions on a stateful model. ```swift let state = model.newState() let prediction = try model.prediction(from: inputFeatures, using: state) ``` - Parameters: - inputFeatures: The input features as declared in the model description. - state: The state object created by `newState()` method. - error: The output parameter to receive an error information on failure.

func (*MLModel) PredictionFromFeaturesUsingStateOptionsCompletionHandler

func (o *MLModel) PredictionFromFeaturesUsingStateOptionsCompletionHandler(inputFeatures MLFeatureProvider, state *MLState, options *MLPredictionOptions, completionHandler func(objc.ID, unsafe.Pointer))

Run a stateful prediction asynchronously. Use this method to run predictions on a stateful model. Do not request a prediction while another prediction that shares the same state is in-flight, otherwise the behavior is undefined. ```swift let state = model.newState() let prediction = try await model.prediction(from: inputFeatures, using: state) ``` - Parameters - input: The input features to make a prediction from. - state: The state object created by `newState()` method. - options: Prediction options to modify how the prediction is run. - completionHandler: A block that will be invoked once the prediction has completed successfully or unsuccessfully. On success, it is invoked with a valid model output. On failure, it is invoked with a nil output and NSError

func (*MLModel) PredictionFromFeaturesUsingStateOptionsError

func (o *MLModel) PredictionFromFeaturesUsingStateOptionsError(inputFeatures MLFeatureProvider, state *MLState, options *MLPredictionOptions) (MLFeatureProvider, error)

Run a stateful prediction synchronously with options. Use this method to run predictions on a stateful model. ```swift let state = model.newState() let prediction = try model.prediction(from: inputFeatures, using: state, options: predictionOptions) ``` - Parameters: - inputFeatures: The input features as declared in the model description. - state: The state object created by `newState()` method. - options: The prediction options. - error: The output parameter to receive an error information on failure.

func (*MLModel) PredictionsFromBatchError

func (o *MLModel) PredictionsFromBatchError(inputBatch MLBatchProvider) (MLBatchProvider, error)

Batch prediction without explicit options

func (*MLModel) PredictionsFromBatchOptionsError

func (o *MLModel) PredictionsFromBatchOptionsError(inputBatch MLBatchProvider, options *MLPredictionOptions) (MLBatchProvider, error)

Batch prediction with explicit options

type MLModelAsset

type MLModelAsset struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelasset

func MLModelAssetFromID

func MLModelAssetFromID(id objc.ID) *MLModelAsset

func MLModelAssetModelAssetWithSpecificationDataBlobMappingError

func MLModelAssetModelAssetWithSpecificationDataBlobMappingError(specificationData *foundation.NSData, blobMapping *foundation.NSDictionary[*foundation.NSURL, *foundation.NSData]) (*MLModelAsset, error)

Construct a model asset from an ML Program specification by replacing blob file references with corresponding in-memory blobs. An ML Program may use `BlobFileValue` syntax, which stores the blob data in external files and refers them by URL. This factory method enables in-memory workflow for such models by using the specified in-memory blob data in place of the external files. The format of in-memory blobs must be the same as the external files. The dictionary must contain all the reference URLs used in the specification. - Parameters: - specification: Contents of .mlmodel as a data blob. - blobMapping: A dictionary with blob URL as the key and blob data as the value. - error: When the model asset creation fails error is populated with the reason for failure.

func MLModelAssetModelAssetWithSpecificationDataError

func MLModelAssetModelAssetWithSpecificationDataError(specificationData *foundation.NSData) (*MLModelAsset, error)

Construct a model asset from the contents of specification data. - Parameters: - specificationData: Contents of .mlmodel as a data blob. - error: When the model asset creation fails error is populated with the reason for failure.

func MLModelAssetModelAssetWithURLError

func MLModelAssetModelAssetWithURLError(compiledModelURL *foundation.NSURL) (*MLModelAsset, error)

Constructs a ModelAsset from a compiled model URL. - Parameters: - compiledModelURL: Location on the disk where the model asset is present. - error: Errors if the model asset is not loadable. - Returns: a model asset or nil if there is an error.

func (*MLModelAsset) FunctionNamesWithCompletionHandler

func (o *MLModelAsset) FunctionNamesWithCompletionHandler(handler objc.Block)

The list of function names in the model asset. Some model types (e.g. ML Program) supports multiple functions. Use this method to query the function names. The method vends the empty array when the model doesn't use the multi-function configuration. ```swift let modelAsset = try MLModelAsset(url: modelURL) let functionNames = try await modelAsset.functionNames print(functionNames) // For example, ["my_function1", "my_function2"]; ```

func (*MLModelAsset) ModelDescriptionOfFunctionNamedCompletionHandler

func (o *MLModelAsset) ModelDescriptionOfFunctionNamedCompletionHandler(functionName *foundation.NSString, handler func(*MLModelDescription, unsafe.Pointer))

The model descripton for a specified function. Use this method to get the description of the model such as the feature descriptions, the model author, and other metadata. ```swift let modelAsset = try MLModelAsset(url: modelURL) let modelDescription = try await modelAsset.modelDescription(of: "my_function") print(modelDescription) ```

func (*MLModelAsset) ModelDescriptionWithCompletionHandler

func (o *MLModelAsset) ModelDescriptionWithCompletionHandler(handler func(*MLModelDescription, unsafe.Pointer))

The default model descripton. Use this method to get the description of the model such as the feature descriptions, the model author, and other metadata. For the multi-function model asset, this method vends the description for the default function. Use `modelDescription(for:)` to get the model description of other functions. ```swift let modelAsset = try MLModelAsset(url: modelURL) let modelDescription = try await modelAsset.modelDescription() print(modelDescription) ```

type MLModelConfiguration

type MLModelConfiguration struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelconfiguration

func MLModelConfigurationFromID

func MLModelConfigurationFromID(id objc.ID) *MLModelConfiguration

func (*MLModelConfiguration) AllowLowPrecisionAccumulationOnGPU

func (o *MLModelConfiguration) AllowLowPrecisionAccumulationOnGPU() bool

Set to YES to allow low precision accumulation on GPU when available. Defaults to NO

func (*MLModelConfiguration) ComputeUnits

func (o *MLModelConfiguration) ComputeUnits() MLComputeUnits

func (*MLModelConfiguration) FunctionName

func (o *MLModelConfiguration) FunctionName() *foundation.NSString

func (*MLModelConfiguration) ModelDisplayName

func (o *MLModelConfiguration) ModelDisplayName() *foundation.NSString

A human readable name of a MLModel instance for display purposes. Use this property to set a name of a model instance so that runtime analysis tools (e.g. Instruments and os_log) can display that name in the user interface. CoreML framework doesn't parse nor filter the text. It is the client's responsibility to use appropriate text, which may involve localization and privacy considerations. When the property is nil, CoreML framework provides a default.

func (*MLModelConfiguration) OptimizationHints

func (o *MLModelConfiguration) OptimizationHints() *MLOptimizationHints

A group of hints for CoreML to optimize

func (*MLModelConfiguration) Parameters

func (*MLModelConfiguration) PreferredMetalDevice

func (o *MLModelConfiguration) PreferredMetalDevice() metal.MTLDevice

Set to specify a preferred Metal device. Defaults to nil which indicates automatic selection

func (*MLModelConfiguration) SetAllowLowPrecisionAccumulationOnGPU

func (o *MLModelConfiguration) SetAllowLowPrecisionAccumulationOnGPU(allowLowPrecisionAccumulationOnGPU bool)

func (*MLModelConfiguration) SetComputeUnits

func (o *MLModelConfiguration) SetComputeUnits(computeUnits MLComputeUnits)

func (*MLModelConfiguration) SetFunctionName

func (o *MLModelConfiguration) SetFunctionName(functionName *foundation.NSString)

func (*MLModelConfiguration) SetModelDisplayName

func (o *MLModelConfiguration) SetModelDisplayName(modelDisplayName *foundation.NSString)

func (*MLModelConfiguration) SetOptimizationHints

func (o *MLModelConfiguration) SetOptimizationHints(optimizationHints *MLOptimizationHints)

func (*MLModelConfiguration) SetParameters

func (o *MLModelConfiguration) SetParameters(parameters *foundation.NSDictionary[*MLParameterKey, objc.ID])

func (*MLModelConfiguration) SetPreferredMetalDevice

func (o *MLModelConfiguration) SetPreferredMetalDevice(preferredMetalDevice metal.MTLDevice)

type MLModelDescription

type MLModelDescription struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodeldescription

func MLModelDescriptionFromID

func MLModelDescriptionFromID(id objc.ID) *MLModelDescription

func (*MLModelDescription) ClassLabels

func (o *MLModelDescription) ClassLabels() *foundation.NSArray[objc.ID]

Array to map a class index to the corresponding label, which is either Number or String. The property is populated from the classLabels entry specified in the model's protobuf message. When the model is a pipeline, which contains one or more sub models, the property value is calculated as follows. 1. If the pipeline model's proto message specifies predictedFeatureName parameter, use classLabels property value of the sub model with the output feature with the name. 2. Otherwise, if the pipeline model has only one sub model with non-nil classLabels property, use the property value. 3. Otherwise, the property is nil.

func (*MLModelDescription) InputDescriptionsByName

Description of the inputs to the model

func (*MLModelDescription) IsUpdatable

func (o *MLModelDescription) IsUpdatable() bool

func (*MLModelDescription) Metadata

Optional metadata describing the model

func (*MLModelDescription) OutputDescriptionsByName

Description of the outputs from the model

func (*MLModelDescription) ParameterDescriptionsByKey

func (*MLModelDescription) PredictedFeatureName

func (o *MLModelDescription) PredictedFeatureName() *foundation.NSString

Name of the primary target / predicted output feature in the output descriptions

func (*MLModelDescription) PredictedProbabilitiesName

func (o *MLModelDescription) PredictedProbabilitiesName() *foundation.NSString

Key for all predicted probabilities stored as a MLFeatureTypeDictionary in the output descriptions

func (*MLModelDescription) StateDescriptionsByName

Description of the state features.

func (*MLModelDescription) TrainingInputDescriptionsByName

func (o *MLModelDescription) TrainingInputDescriptionsByName() *foundation.NSDictionary[*foundation.NSString, *MLFeatureDescription]

type MLModelError

type MLModelError int64
const (
	// Core ML throws/returns this error when the framework encounters an generic error. The typical cause for this error is an unexpected framework level problem.
	MLModelErrorGeneric MLModelError = 0
	// Core ML throws/returns this error when the model client, typically an application, sends the wrong feature type to a model's input. The typical cause for this error is a programming mistake. For example, a prediction method will throw/return the error when the caller passes an image to a model's input that expects an `MLMultiArray`.
	MLModelErrorFeatureType MLModelError = 1
	// Core ML throws/returns this error when the framework encounters some I/O problem, most likely a file I/O problem. For example, a model loading will throw/return the error when the caller requests a non-existing model URL.
	MLModelErrorIO MLModelError = 3
	// Core ML throws/returns this error when the framework encounters an error in the custom layer subsystem. The typical cause for this error is a programming mistake. For example, a prediction method will throw/return the error when it fails to find the custom layer implementation.
	MLModelErrorCustomLayer MLModelError = 4
	// Core ML throws/returns this error when the framework encounters an error in the custom model subsystem. The typical cause for this error is a programming mistake. For example, a prediction method will throw/return the error when it fails to find the custom model implementation.
	MLModelErrorCustomModel MLModelError = 5
	// Core ML throws/returns this error when the framework encounters an error while performing the on-device model update. For example, the framework will throw/return the error when it fails to save the updated model.
	MLModelErrorUpdate MLModelError = 6
	// Core ML throws/returns this error when the model client, typically an application, queries an unsupported model parameter (see MLParameterKey). The typical cause for this error is a programming mistake.
	MLModelErrorParameters MLModelError = 7
	// Core ML throws/returns this error when the framework fails to download the model decryption key. The typical cause for this error is a network connection issue to the key server.
	MLModelErrorModelDecryptionKeyFetch MLModelError = 8
	// Core ML throws/returns this error when the framework encounters an error in the model decryption subsystem. The typical cause for this error is in the key server configuration and the client application cannot do much about it. For example, a model loading method will throw/return the error when it uses incorrect model decryption key.
	MLModelErrorModelDecryption MLModelError = 9
	// Core ML throws/returns this error when the framework encounters an error in the model collection deployment subsystem. The typical cause for this error is the network connectability issue to the model deployment server.
	MLModelErrorModelCollection MLModelError = 10
	// Core ML throws/returns this error when the prediction is cancelled prior to completing.
	MLModelErrorPredictionCancelled MLModelError = 11
)

func (MLModelError) String

func (e MLModelError) String() string

type MLModelStructure

type MLModelStructure struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructure

func MLModelStructureFromID

func MLModelStructureFromID(id objc.ID) *MLModelStructure

func (*MLModelStructure) NeuralNetwork

func (o *MLModelStructure) NeuralNetwork() *MLModelStructureNeuralNetwork

If the model is of NeuralNetwork type then it is the structure of the NeuralNetwork otherwise `nil`.

func (*MLModelStructure) Pipeline

If the model is of Pipeline type then it is the structure of the Pipeline otherwise `nil`.

func (*MLModelStructure) Program

If the model is of ML Program type then it is the structure of the ML Program otherwise `nil`.

type MLModelStructureNeuralNetwork

type MLModelStructureNeuralNetwork struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureneuralnetwork

func MLModelStructureNeuralNetworkFromID

func MLModelStructureNeuralNetworkFromID(id objc.ID) *MLModelStructureNeuralNetwork

func (*MLModelStructureNeuralNetwork) Layers

type MLModelStructureNeuralNetworkLayer

type MLModelStructureNeuralNetworkLayer struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureneuralnetworklayer

func MLModelStructureNeuralNetworkLayerFromID

func MLModelStructureNeuralNetworkLayerFromID(id objc.ID) *MLModelStructureNeuralNetworkLayer

func (*MLModelStructureNeuralNetworkLayer) InputNames

The input names.

func (*MLModelStructureNeuralNetworkLayer) Name

The layer name.

func (*MLModelStructureNeuralNetworkLayer) OutputNames

The output names.

func (*MLModelStructureNeuralNetworkLayer) Type

The type of the layer, e,g, "elementwise", "pooling", etc.

type MLModelStructurePipeline

type MLModelStructurePipeline struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructurepipeline

func MLModelStructurePipelineFromID

func MLModelStructurePipelineFromID(id objc.ID) *MLModelStructurePipeline

func (*MLModelStructurePipeline) SubModelNames

The names of the sub models in the pipeline.

func (*MLModelStructurePipeline) SubModels

The structure of the sub models in the pipeline.

type MLModelStructureProgram

type MLModelStructureProgram struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogram

func MLModelStructureProgramFromID

func MLModelStructureProgramFromID(id objc.ID) *MLModelStructureProgram

type MLModelStructureProgramArgument

type MLModelStructureProgramArgument struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogramargument

func MLModelStructureProgramArgumentFromID

func MLModelStructureProgramArgumentFromID(id objc.ID) *MLModelStructureProgramArgument

func (*MLModelStructureProgramArgument) Bindings

type MLModelStructureProgramBinding

type MLModelStructureProgramBinding struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogrambinding

func MLModelStructureProgramBindingFromID

func MLModelStructureProgramBindingFromID(id objc.ID) *MLModelStructureProgramBinding

func (*MLModelStructureProgramBinding) Name

The name of the variable in the Program.

func (*MLModelStructureProgramBinding) Value

The compile time constant value in the Program.

type MLModelStructureProgramBlock

type MLModelStructureProgramBlock struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogramblock

func MLModelStructureProgramBlockFromID

func MLModelStructureProgramBlockFromID(id objc.ID) *MLModelStructureProgramBlock

func (*MLModelStructureProgramBlock) Inputs

The named inputs to the block.

func (*MLModelStructureProgramBlock) Operations

The list of topologically sorted operations in the block.

func (*MLModelStructureProgramBlock) OutputNames

The output names.

type MLModelStructureProgramFunction

type MLModelStructureProgramFunction struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogramfunction

func MLModelStructureProgramFunctionFromID

func MLModelStructureProgramFunctionFromID(id objc.ID) *MLModelStructureProgramFunction

func (*MLModelStructureProgramFunction) Block

The active block in the function.

func (*MLModelStructureProgramFunction) Inputs

The named inputs to the function.

type MLModelStructureProgramNamedValueType

type MLModelStructureProgramNamedValueType struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogramnamedvaluetype

func MLModelStructureProgramNamedValueTypeFromID

func MLModelStructureProgramNamedValueTypeFromID(id objc.ID) *MLModelStructureProgramNamedValueType

func (*MLModelStructureProgramNamedValueType) Name

The name of the parameter.

func (*MLModelStructureProgramNamedValueType) Type

The type of the parameter.

type MLModelStructureProgramOperation

type MLModelStructureProgramOperation struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogramoperation

func MLModelStructureProgramOperationFromID

func MLModelStructureProgramOperationFromID(id objc.ID) *MLModelStructureProgramOperation

func (*MLModelStructureProgramOperation) Blocks

Nested blocks for loops and conditionals, e.g., a conditional block will have two entries here.

func (*MLModelStructureProgramOperation) Inputs

The arguments to the Operation.

func (*MLModelStructureProgramOperation) OperatorName

The name of the operator, e.g., "conv", "pool", "softmax", etc.

func (*MLModelStructureProgramOperation) Outputs

The outputs of the Operation.

type MLModelStructureProgramValue

type MLModelStructureProgramValue struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmodelstructureprogramvalue

func MLModelStructureProgramValueFromID

func MLModelStructureProgramValueFromID(id objc.ID) *MLModelStructureProgramValue

type MLMultiArray

type MLMultiArray struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmultiarray

func MLMultiArrayFromID

func MLMultiArrayFromID(id objc.ID) *MLMultiArray

func MLMultiArrayMultiArrayByConcatenatingMultiArraysAlongAxisDataType

func MLMultiArrayMultiArrayByConcatenatingMultiArraysAlongAxisDataType(multiArrays *foundation.NSArray[*MLMultiArray], axis int, dataType MLMultiArrayDataType) *MLMultiArray

Concatenate MLMultiArrays to form a new MLMultiArray. All the source MLMultiArrays must have a same shape except the specified axis. The resultant MLMultiArray has the same shape as inputs except this axis, which dimension will be the sum of all the input dimensions of the axis. For example, ```swift // Swift let A = try MLMultiArray(shape: [2, 3], dataType: .int32) let B = try MLMultiArray(shape: [2, 2], dataType: .int32) let C = MLMultiArray(concatenating: [A, B], axis: 1, dataType: .int32) assert(C.shape == [2, 5]) ``` ```objc // Obj-C MLMultiArray *A = [[MLMultiArray alloc] initWithShape:@[@2, @3] dataType:MLMultiArrayDataTypeInt32 error:NULL]; MLMultiArray *B = [[MLMultiArray alloc] initWithShape:@[@2, @2] dataType:MLMultiArrayDataTypeInt32 error:NULL]; MLMultiArray *C = [MLMultiArray multiArrayByConcatenatingMultiArrays:@[A, B] alongAxis:1 dataType:MLMultiArrayDataTypeInt32]; assert(C.shape == @[@2, @5]) ``` Numeric data will be up or down casted as needed. The method raises NSInvalidArgumentException if the shapes of input multi arrays are not compatible for concatenation. - Parameters: - multiArrays: Array of MLMultiArray instances to be concatenated. - axis: Axis index with which the concatenation will performed. The value is wrapped by the dimension of the axis. For example, -1 is the last axis. - dataType: The data type of the resultant MLMultiArray.

func (*MLMultiArray) Count

func (o *MLMultiArray) Count() int

Count of total number of addressable scalars. The value is same as `product_d shape[d]`.

func (*MLMultiArray) DataPointer

func (o *MLMultiArray) DataPointer() unsafe.Pointer

Unsafe pointer to underlying buffer holding the data Deprecated: Use getBytesWithHandler or getMutableBytesWithHandler instead. For Swift, use withUnsafeBytes or withUnsafeMutableBytes.

func (*MLMultiArray) DataType

func (o *MLMultiArray) DataType() MLMultiArrayDataType

Scalar's data type. Deprecated: Use getBytesWithHandler or getMutableBytesWithHandler instead. For Swift, use withUnsafeBytes or withUnsafeMutableBytes.

func (*MLMultiArray) GetBytesWithHandler

func (o *MLMultiArray) GetBytesWithHandler(handler func(unsafe.Pointer, int))

Get the underlying buffer pointer to read. The buffer pointer is valid only within the block. ```objc MLMultiArray * A = [[MLMultiArray alloc] initWithShape:@[@3, @2] dataType:MLMultiArrayDataTypeInt32 error:NULL]; A[@[@1, @2]] = @42; [A getBytesWithHandler:^(const void *bytes, NSInteger size) { const int32_t *scalarBuffer = (const int32_t *)bytes; const int strideY = A.strides[0].intValue; // Print 42 NSLog(@"Scalar at (1, 2): %d", scalarBuffer[1 * strideY + 2]); }]; ``` - Parameters: - handler: The block to receive the buffer pointer and its size in bytes.

func (*MLMultiArray) GetMutableBytesWithHandler

func (o *MLMultiArray) GetMutableBytesWithHandler(handler objc.Block)

Get the underlying buffer pointer to mutate. The buffer pointer is valid only within the block. Use `strides` parameter passed in the block because the method may switch to a new backing buffer with different strides. ```objc MLMultiArray * A = [[MLMultiArray alloc] initWithShape:@[@3, @2] dataType:MLMultiArrayDataTypeInt32 error:NULL]; [A getMutableBytesWithHandler:^(void *bytes, NSInteger __unused size, NSArray<NSNumber *> *strides) { int32_t *scalarBuffer = (int32_t *)bytes; const int strideY = strides[0].intValue; scalarBuffer[1 * strideY + 2] = 42; // Set 42 at A[1, 2] }]; ``` - Parameters: - handler: The block to receive the buffer pointer, size in bytes, and strides.

func (*MLMultiArray) InitWithDataPointerShapeDataTypeStridesDeallocatorError

func (o *MLMultiArray) InitWithDataPointerShapeDataTypeStridesDeallocatorError(dataPointer unsafe.Pointer, shape *foundation.NSArray[*foundation.NSNumber], dataType MLMultiArrayDataType, strides *foundation.NSArray[*foundation.NSNumber], deallocator func(unsafe.Pointer)) (*MLMultiArray, error)

Creates the object with existing data without copy. Use this initializer to reference the existing buffer as the storage without copy. ```objc int32_t *buffer = malloc(sizeof(int32_t) * 2 * 3 * 4); MLMultiArray *multiArray = [[MLMultiArray alloc] initWithDataPointer:buffer shape:@[@2, @3, @4] dataType:MLMultiArrayDataTypeInt32 strides:@[@12, @4, @1] deallocator:^(void *bytes) { free(bytes); } error:NULL]; ``` - Parameters: - dataPointer: The pointer to the buffer. - shape: The shape - dataType: The data type - strides: The strides. - deallocator: Block to be called on the deallocation of the instance. - error: Filled with error information on error.

func (*MLMultiArray) InitWithPixelBufferShape

func (o *MLMultiArray) InitWithPixelBufferShape(pixelBuffer unsafe.Pointer, shape *foundation.NSArray[*foundation.NSNumber]) *MLMultiArray

Create by wrapping a pixel buffer. Use this initializer to create an IOSurface backed MLMultiArray, which can reduce the inference latency by avoiding the buffer copy. The instance will own the pixel buffer and release it on the deallocation. The pixel buffer's pixel format type must be either `kCVPixelFormatType_OneComponent16Half` for `MLMultiArrayDataTypeFloat16` or `kCVPixelFormatType_OneComponent8` for `MLMultiArrayDataTypeInt8`. ```objc CVPixelBufferRef pixelBuffer = NULL; NSDictionary* pixelBufferAttributes = @{ (id)kCVPixelBufferIOSurfacePropertiesKey: @{} }; // Since shape == [2, 3, 4], width is 4 (= shape[2]) and height is 6 (= shape[0] * shape[1]). CVPixelBufferCreate(kCFAllocatorDefault, 4, 6, kCVPixelFormatType_OneComponent16Half, (__bridge CFDictionaryRef)pixelBufferAttributes, &pixelBuffer); MLMultiArray *multiArray = [[MLMultiArray alloc] initWithPixelBuffer:pixelBuffer shape:@[@2, @3, @4]]; ``` - Parameters: - pixelBuffer: The pixel buffer to be owned by the instance. - shape: The shape of the MLMultiArray. The last dimension of `shape` must match the pixel buffer's width. The product of the rest of the dimensions must match the height.

func (*MLMultiArray) InitWithShapeDataTypeError

func (o *MLMultiArray) InitWithShapeDataTypeError(shape *foundation.NSArray[*foundation.NSNumber], dataType MLMultiArrayDataType) (*MLMultiArray, error)

Creates the object. The contents of the object are left uninitialized; the client must initialize it. The scalars will use the first-major contiguous layout. - Parameters: - shape: The shape - dataType: The data type - error: Filled with error information on error.

func (*MLMultiArray) InitWithShapeDataTypeStrides

func (o *MLMultiArray) InitWithShapeDataTypeStrides(shape *foundation.NSArray[*foundation.NSNumber], dataType MLMultiArrayDataType, strides *foundation.NSArray[*foundation.NSNumber]) *MLMultiArray

Creates the object with specified strides. The contents of the object are left uninitialized; the client must initialize it. ```swift let shape = [2, 3]; let strides = [4, 1] let multiArray = MLMultiArray(shape: shape, dataType: .float32, strides: strides) XCTAssertEqual(multiArray.shape, shape as [NSNumber]) XCTAssertEqual(multiArray.strides, strides as [NSNumber]) ``` ```objc NSArray<NSNumber *> *shape = @[@2, @3]; NSArray<NSNumber *> *strides = @[@4, @1]; MLMultiArray *multiArray = [[MLMultiArray alloc] initWithShape:shape dataType:MLMultiArrayDataTypeFloat32 strides:strides]; XCTAssertEqualObjects(multiArray.shape, shape); XCTAssertEqualObjects(multiArray.strides, strides); ``` - Parameters: - shape: The shape - dataType: The data type - strides: The strides.

func (*MLMultiArray) ObjectAtIndexedSubscript

func (o *MLMultiArray) ObjectAtIndexedSubscript(idx int) *foundation.NSNumber

Get a value by its linear index (assumes C-style index ordering)

func (*MLMultiArray) ObjectForKeyedSubscript

func (o *MLMultiArray) ObjectForKeyedSubscript(key *foundation.NSArray[*foundation.NSNumber]) *foundation.NSNumber

Get a value by its multidimensional index (NSArray<NSNumber *>)

func (*MLMultiArray) PixelBuffer

func (o *MLMultiArray) PixelBuffer() unsafe.Pointer

Returns the backing pixel buffer if exists, otherwise nil.

func (*MLMultiArray) SetObjectAtIndexedSubscript

func (o *MLMultiArray) SetObjectAtIndexedSubscript(obj *foundation.NSNumber, idx int)

Set a value by its linear index (assumes C-style index ordering)

func (*MLMultiArray) SetObjectForKeyedSubscript

func (o *MLMultiArray) SetObjectForKeyedSubscript(obj *foundation.NSNumber, key *foundation.NSArray[*foundation.NSNumber])

Set a value by subindicies (NSArray<NSNumber *>)

func (*MLMultiArray) Shape

Shape of the multi-dimensional space that this instance represents.

func (*MLMultiArray) Strides

Strides. It defines the offset of the scalar of a given coordinate index in the storage, which is: ``` scalarOffset = sum_d index[d]*strides[d] ```

func (*MLMultiArray) TransferToMultiArray

func (o *MLMultiArray) TransferToMultiArray(destinationMultiArray *MLMultiArray)

Transfer the contents to the destination multi-array. Numeric data will be up or down casted as needed. It can transfer to a multi-array with different layout (strides). ```swift let sourceMultiArray: MLMultiArray = ... // shape is [2, 3] and data type is Float64 let newStrides = [4, 1] let destinationMultiArray = MLMultiArray(shape: [2, 3], dataType: .float32, strides: newStrides) sourceMultiArray.transfer(to: destinationMultiArray) ``` ```objc NSArray<NSNumber *> *shape = @[@2, @3]; NSArray<NSNumber *> *sourceStrides = @[@3, @1]; NSArray<NSNumber *> *destinationStrides = @[@4, @1]; MLMultiArray *source = [[MLMultiArray alloc] initWithShape:shape dataType:MLMultiArrayDataTypeDouble strides:sourceStrides]; // Initialize source... MLMultiArray *destination = [[MLMultiArray alloc] initWithShape:shape dataType:MLMultiArrayDataTypeFloat32 strides:destinationStrides]; [source transferToMultiArray:destination]; ``` - Parameters: - destinationMultiArray: The transfer destination.

type MLMultiArrayConstraint

type MLMultiArrayConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmultiarrayconstraint

func MLMultiArrayConstraintFromID

func MLMultiArrayConstraintFromID(id objc.ID) *MLMultiArrayConstraint

func (*MLMultiArrayConstraint) DataType

func (*MLMultiArrayConstraint) Shape

func (*MLMultiArrayConstraint) ShapeConstraint

type MLMultiArrayDataType

type MLMultiArrayDataType int64
const (
	MLMultiArrayDataTypeDouble  MLMultiArrayDataType = 65600
	MLMultiArrayDataTypeFloat64 MLMultiArrayDataType = 65600
	MLMultiArrayDataTypeFloat32 MLMultiArrayDataType = 65568
	MLMultiArrayDataTypeFloat16 MLMultiArrayDataType = 65552
	MLMultiArrayDataTypeFloat   MLMultiArrayDataType = 65568
	MLMultiArrayDataTypeInt32   MLMultiArrayDataType = 131104
	MLMultiArrayDataTypeInt8    MLMultiArrayDataType = 131080
)

func (MLMultiArrayDataType) String

func (e MLMultiArrayDataType) String() string

type MLMultiArrayShapeConstraint

type MLMultiArrayShapeConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlmultiarrayshapeconstraint

func MLMultiArrayShapeConstraintFromID

func MLMultiArrayShapeConstraintFromID(id objc.ID) *MLMultiArrayShapeConstraint

func (*MLMultiArrayShapeConstraint) EnumeratedShapes

func (o *MLMultiArrayShapeConstraint) EnumeratedShapes() *foundation.NSArray[objc.ID]

func (*MLMultiArrayShapeConstraint) SizeRangeForDimension

func (o *MLMultiArrayShapeConstraint) SizeRangeForDimension() *foundation.NSArray[*foundation.NSValue]

func (*MLMultiArrayShapeConstraint) Type

type MLMultiArrayShapeConstraintType

type MLMultiArrayShapeConstraintType int64
const (
	MLMultiArrayShapeConstraintTypeUnspecified MLMultiArrayShapeConstraintType = 1
	MLMultiArrayShapeConstraintTypeEnumerated  MLMultiArrayShapeConstraintType = 2
	MLMultiArrayShapeConstraintTypeRange       MLMultiArrayShapeConstraintType = 3
)

func (MLMultiArrayShapeConstraintType) String

type MLNeuralEngineComputeDevice

type MLNeuralEngineComputeDevice struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlneuralenginecomputedevice

func MLNeuralEngineComputeDeviceFromID

func MLNeuralEngineComputeDeviceFromID(id objc.ID) *MLNeuralEngineComputeDevice

func (*MLNeuralEngineComputeDevice) TotalCoreCount

func (o *MLNeuralEngineComputeDevice) TotalCoreCount() int

type MLNumericConstraint

type MLNumericConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlnumericconstraint

func MLNumericConstraintFromID

func MLNumericConstraintFromID(id objc.ID) *MLNumericConstraint

func (*MLNumericConstraint) EnumeratedNumbers

func (o *MLNumericConstraint) EnumeratedNumbers() *foundation.NSSet[*foundation.NSNumber]

func (*MLNumericConstraint) MaxNumber

func (o *MLNumericConstraint) MaxNumber() *foundation.NSNumber

func (*MLNumericConstraint) MinNumber

func (o *MLNumericConstraint) MinNumber() *foundation.NSNumber

type MLOptimizationHints

type MLOptimizationHints struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mloptimizationhints

func MLOptimizationHintsFromID

func MLOptimizationHintsFromID(id objc.ID) *MLOptimizationHints

func (*MLOptimizationHints) ReshapeFrequency

func (o *MLOptimizationHints) ReshapeFrequency() MLReshapeFrequencyHint

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

func (*MLOptimizationHints) SetReshapeFrequency

func (o *MLOptimizationHints) SetReshapeFrequency(reshapeFrequency MLReshapeFrequencyHint)

func (*MLOptimizationHints) SetSpecializationStrategy

func (o *MLOptimizationHints) SetSpecializationStrategy(specializationStrategy MLSpecializationStrategy)

func (*MLOptimizationHints) SpecializationStrategy

func (o *MLOptimizationHints) SpecializationStrategy() MLSpecializationStrategy

Optimization strategy for the model specialization. Core ML segments the model's compute graph and optimizes 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 application.

type MLParameterDescription

type MLParameterDescription struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlparameterdescription

func MLParameterDescriptionFromID

func MLParameterDescriptionFromID(id objc.ID) *MLParameterDescription

func (*MLParameterDescription) DefaultValue

func (o *MLParameterDescription) DefaultValue() objc.ID

func (*MLParameterDescription) Key

func (*MLParameterDescription) NumericConstraint

func (o *MLParameterDescription) NumericConstraint() *MLNumericConstraint

type MLParameterKey

type MLParameterKey struct {
	MLKey
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlparameterkey

func MLParameterKeyBeta1

func MLParameterKeyBeta1() *MLParameterKey

func MLParameterKeyBeta2

func MLParameterKeyBeta2() *MLParameterKey

func MLParameterKeyBiases

func MLParameterKeyBiases() *MLParameterKey

func MLParameterKeyEpochs

func MLParameterKeyEpochs() *MLParameterKey

func MLParameterKeyEps

func MLParameterKeyEps() *MLParameterKey

func MLParameterKeyFromID

func MLParameterKeyFromID(id objc.ID) *MLParameterKey

func MLParameterKeyLearningRate

func MLParameterKeyLearningRate() *MLParameterKey

func MLParameterKeyLinkedModelFileName

func MLParameterKeyLinkedModelFileName() *MLParameterKey

func MLParameterKeyLinkedModelSearchPath

func MLParameterKeyLinkedModelSearchPath() *MLParameterKey

func MLParameterKeyMiniBatchSize

func MLParameterKeyMiniBatchSize() *MLParameterKey

func MLParameterKeyMomentum

func MLParameterKeyMomentum() *MLParameterKey

func MLParameterKeyNumberOfNeighbors

func MLParameterKeyNumberOfNeighbors() *MLParameterKey

func MLParameterKeySeed

func MLParameterKeySeed() *MLParameterKey

func MLParameterKeyShuffle

func MLParameterKeyShuffle() *MLParameterKey

func MLParameterKeyWeights

func MLParameterKeyWeights() *MLParameterKey

func (*MLParameterKey) ScopedTo

func (o *MLParameterKey) ScopedTo(scope *foundation.NSString) *MLParameterKey

type MLPredictionOptions

type MLPredictionOptions struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlpredictionoptions

func MLPredictionOptionsFromID

func MLPredictionOptionsFromID(id objc.ID) *MLPredictionOptions

func (*MLPredictionOptions) OutputBackings

@abstract Propose the model to use the specified backing objects for the output feature values. @discussion Use the property to get the inference result directly into the client allocated buffer when possible for efficient memory management. The property is a dictionary of the feature name and the output backing object. The framework may not use the specified backing object and instead allocates one by itself if the outputBacking dictionary doesn't contain the entry for the feature name, the model doesn't support the user allocated buffers, or in the batch prediction mode. To check if the backing object was used, compare the output prediction and the backing object by object identity. \code CVPixelBufferRef outputBacking = ...; [options setOutputBackings:@{@"outputImage" : (__bridge id)outputBacking}]; id<MLFeatureProvider> prediction = [model predictionFromFeatures:inputFeatures options:options error:&error]; if ([prediction featureValueForName:@"outputImage"].imageBufferValue == outputBacking) { // backing was used. } else { // backing was NOT used. } \endcode The backing object must be either CVPixelBuffer or MLMultiArray depending on the feature value type. Do not lock the base address of the CVPixelBuffer. In the case of a MLMultiArray backed by a pixel buffer, make sure not to lock the underlying pixel buffer by not calling any data methods such as `.dataPointer` and subscript methods before the prediction. The framework ignores a backing object with an unknown feature name. For the best performance, use page-aligned address in MLMultiArray. \code #import <mach/vm_page_size.h> : void *backingBuffer = aligned_alloc(vm_page_size, round_page(backingBufferSize)); if (backingBuffer == NULL) { ... error handling ... } MLMultiArray *outputBacking = [[MLMultiArray alloc] initWithDataPointer:(char *)backingBuffer ... deallocator:^(void *) { free(backingBuffer); } ... ]; \endcode For CVPixelBuffer backing, consider to use IOSurface-backed CVPixelBuffer created by CVPixelBufferPool because it is often the most efficient choice for memory footprint and performance, especially when the pixel buffers are subsequently used for playback or export. (See also AVSampleBufferDisplayLayer and AVAssetWriter.) The output backing object must satisfy the output feature description's `-isAllowedValue:` test, or the framework reporets an error at the prediction time. The exception is FP16 MLMultiArray backed by CVPixelBuffer, which may be accepted in Double or Float32 multi array output feature depending on the underlying inference engine.

func (*MLPredictionOptions) SetOutputBackings

func (o *MLPredictionOptions) SetOutputBackings(outputBackings *foundation.NSDictionary[*foundation.NSString, objc.ID])

func (*MLPredictionOptions) SetUsesCPUOnly deprecated

func (o *MLPredictionOptions) SetUsesCPUOnly(usesCPUOnly bool)

Deprecated: since macOS 12.0.

func (*MLPredictionOptions) UsesCPUOnly

func (o *MLPredictionOptions) UsesCPUOnly() bool

Set to YES to force computation to be on the CPU only Deprecated: since macOS 12.0.

type MLReshapeFrequencyHint

type MLReshapeFrequencyHint int64
const (
	// The input shape is expected to change frequently on each prediction sent to this loaded model instance. Core ML will try to minimize the latency associated with shape changes and avoid expensive shape-specific optimizations prior to prediction computation. While prediction computation may be slower for each specific shape, switching between shapes should be faster. This is the default.
	MLReshapeFrequencyHintFrequent MLReshapeFrequencyHint = 0
	// The input shape is expected to be stable and many/all predictions sent to this loaded model instance would use the same input shapes repeatedly. On the shape change, Core ML re-optimizes the internal engine for the new shape if possible. The re-optimization takes some time, but the subsequent predictions for the shape should run faster.
	MLReshapeFrequencyHintInfrequent MLReshapeFrequencyHint = 1
)

func (MLReshapeFrequencyHint) String

func (e MLReshapeFrequencyHint) String() string

type MLSequence

type MLSequence struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlsequence

func MLSequenceEmptySequenceWithType

func MLSequenceEmptySequenceWithType(type_ MLFeatureType) *MLSequence

Empty sequence of a sepcific type

func MLSequenceFromID

func MLSequenceFromID(id objc.ID) *MLSequence

func MLSequenceSequenceWithInt64Array

func MLSequenceSequenceWithInt64Array(int64Values *foundation.NSArray[*foundation.NSNumber]) *MLSequence

int64 sequence, propery will be empty array if type is MLFeatureTypeInt64

func MLSequenceSequenceWithStringArray

func MLSequenceSequenceWithStringArray(stringValues *foundation.NSArray[*foundation.NSString]) *MLSequence

String sequences, property will be empty array if type is MLFeatureTypeString

func (*MLSequence) Int64Values

func (o *MLSequence) Int64Values() *foundation.NSArray[*foundation.NSNumber]

func (*MLSequence) StringValues

func (o *MLSequence) StringValues() *foundation.NSArray[*foundation.NSString]

func (*MLSequence) Type

func (o *MLSequence) Type() MLFeatureType

Type of values held

type MLSequenceConstraint

type MLSequenceConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlsequenceconstraint

func MLSequenceConstraintFromID

func MLSequenceConstraintFromID(id objc.ID) *MLSequenceConstraint

func (*MLSequenceConstraint) CountRange

func (o *MLSequenceConstraint) CountRange() foundation.NSRange

func (*MLSequenceConstraint) ValueDescription

func (o *MLSequenceConstraint) ValueDescription() *MLFeatureDescription

type MLSpecializationStrategy

type MLSpecializationStrategy int64
const (
	// The strategy that works well for most applications.
	MLSpecializationStrategyDefault MLSpecializationStrategy = 0
	// Prefer the prediction latency at the potential cost of specialization time, memory footprint, and the disk space usage of specialized artifacts.
	MLSpecializationStrategyFastPrediction MLSpecializationStrategy = 1
)

func (MLSpecializationStrategy) String

func (e MLSpecializationStrategy) String() string

type MLState

type MLState struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlstate

func MLStateFromID

func MLStateFromID(id objc.ID) *MLState

func (*MLState) GetMultiArrayForStateNamedHandler

func (o *MLState) GetMultiArrayForStateNamedHandler(stateName *foundation.NSString, handler func(*MLMultiArray))

Gets a mutable view into a state buffer. The underlying state buffer's address can differ for each call; one shall not access the state buffer outside of the closure. - Parameters: - handler: Block to access the state buffer through `MLMultiArray`.

type MLStateConstraint

type MLStateConstraint struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlstateconstraint

func MLStateConstraintFromID

func MLStateConstraintFromID(id objc.ID) *MLStateConstraint

func (*MLStateConstraint) BufferShape

The shape of the state buffer.

func (*MLStateConstraint) DataType

The data type of scalars in the state buffer.

type MLTask

type MLTask struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mltask

func MLTaskFromID

func MLTaskFromID(id objc.ID) *MLTask

func (*MLTask) Cancel

func (o *MLTask) Cancel()

func (*MLTask) Error

func (o *MLTask) Error() unsafe.Pointer

func (*MLTask) Resume

func (o *MLTask) Resume()

func (*MLTask) State

func (o *MLTask) State() MLTaskState

func (*MLTask) TaskIdentifier

func (o *MLTask) TaskIdentifier() *foundation.NSString

type MLTaskState

type MLTaskState int64
const (
	MLTaskStateSuspended  MLTaskState = 1
	MLTaskStateRunning    MLTaskState = 2
	MLTaskStateCancelling MLTaskState = 3
	MLTaskStateCompleted  MLTaskState = 4
	MLTaskStateFailed     MLTaskState = 5
)

func (MLTaskState) String

func (e MLTaskState) String() string

type MLUpdateContext

type MLUpdateContext struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlupdatecontext

func MLUpdateContextFromID

func MLUpdateContextFromID(id objc.ID) *MLUpdateContext

func (*MLUpdateContext) Event

func (*MLUpdateContext) Metrics

func (*MLUpdateContext) Model

func (o *MLUpdateContext) Model() *MLModel

func (*MLUpdateContext) Parameters

func (*MLUpdateContext) Task

func (o *MLUpdateContext) Task() *MLUpdateTask

type MLUpdateProgressEvent

type MLUpdateProgressEvent int64
const (
	MLUpdateProgressEventTrainingBegin MLUpdateProgressEvent = 1
	MLUpdateProgressEventEpochEnd      MLUpdateProgressEvent = 2
	MLUpdateProgressEventMiniBatchEnd  MLUpdateProgressEvent = 4
)

func (MLUpdateProgressEvent) String

func (e MLUpdateProgressEvent) String() string

type MLUpdateProgressHandlers

type MLUpdateProgressHandlers struct {
	foundation.NSObject
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlupdateprogresshandlers

func MLUpdateProgressHandlersFromID

func MLUpdateProgressHandlersFromID(id objc.ID) *MLUpdateProgressHandlers

func (*MLUpdateProgressHandlers) InitForEventsProgressHandlerCompletionHandler

func (o *MLUpdateProgressHandlers) InitForEventsProgressHandlerCompletionHandler(interestedEvents MLUpdateProgressEvent, progressHandler func(*MLUpdateContext), completionHandler func(*MLUpdateContext)) *MLUpdateProgressHandlers

type MLUpdateTask

type MLUpdateTask struct {
	MLTask
}

Apple documentation: https://developer.apple.com/documentation/coreml/mlupdatetask

func MLUpdateTaskFromID

func MLUpdateTaskFromID(id objc.ID) *MLUpdateTask

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataCompletionHandlerError

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataCompletionHandlerError(modelURL *foundation.NSURL, trainingData MLBatchProvider, completionHandler func(*MLUpdateContext)) (*MLUpdateTask, error)

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataConfigurationCompletionHandlerError

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataConfigurationCompletionHandlerError(modelURL *foundation.NSURL, trainingData MLBatchProvider, configuration *MLModelConfiguration, completionHandler func(*MLUpdateContext)) (*MLUpdateTask, error)

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataConfigurationProgressHandlersError

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataConfigurationProgressHandlersError(modelURL *foundation.NSURL, trainingData MLBatchProvider, configuration *MLModelConfiguration, progressHandlers *MLUpdateProgressHandlers) (*MLUpdateTask, error)

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataProgressHandlersError

func MLUpdateTaskUpdateTaskForModelAtURLTrainingDataProgressHandlersError(modelURL *foundation.NSURL, trainingData MLBatchProvider, progressHandlers *MLUpdateProgressHandlers) (*MLUpdateTask, error)

func (*MLUpdateTask) ResumeWithParameters

func (o *MLUpdateTask) ResumeWithParameters(updateParameters *foundation.NSDictionary[*MLParameterKey, objc.ID])

type MLWritable

type MLWritable interface {
}

MLWritable wraps the ObjC protocol MLWritable.

type MTLCommandBuffer

type MTLCommandBuffer interface {
}

MTLCommandBuffer wraps the ObjC protocol MTLCommandBuffer.

type MTLDevice

type MTLDevice interface {
}

MTLDevice wraps the ObjC protocol MTLDevice.

type MTLTexture

type MTLTexture interface {
}

MTLTexture wraps the ObjC protocol MTLTexture.

type Mach_vm_range_flags_t

type Mach_vm_range_flags_t int64
const (
	MACH_VM_RANGE_NONE Mach_vm_range_flags_t = 0
)

func (Mach_vm_range_flags_t) String

func (e Mach_vm_range_flags_t) String() string

type Mach_vm_range_flavor_t

type Mach_vm_range_flavor_t int64
const (
	MACH_VM_RANGE_FLAVOR_INVALID Mach_vm_range_flavor_t = 0
	MACH_VM_RANGE_FLAVOR_V1      Mach_vm_range_flavor_t = 1
)

func (Mach_vm_range_flavor_t) String

func (e Mach_vm_range_flavor_t) String() string

type Mach_vm_range_tag_t

type Mach_vm_range_tag_t int64
const (
	MACH_VM_RANGE_DEFAULT Mach_vm_range_tag_t = 0
	MACH_VM_RANGE_DATA    Mach_vm_range_tag_t = 1
	MACH_VM_RANGE_FIXED   Mach_vm_range_tag_t = 2
)

func (Mach_vm_range_tag_t) String

func (e Mach_vm_range_tag_t) String() string

type Mpo_flags_t

type Mpo_flags_t int64
const (
	MPO_PORT                            Mpo_flags_t = 0
	MPO_SERVICE_PORT                    Mpo_flags_t = 1024
	MPO_CONNECTION_PORT                 Mpo_flags_t = 2048
	MPO_REPLY_PORT                      Mpo_flags_t = 4096
	MPO_WEAK_REPLY_PORT                 Mpo_flags_t = 16384
	MPO_NOTIFICATION_PORT               Mpo_flags_t = 17408
	MPO_EXCEPTION_PORT                  Mpo_flags_t = 32768
	MPO_CONNECTION_PORT_WITH_PORT_ARRAY Mpo_flags_t = 65536
)

func (Mpo_flags_t) String

func (e Mpo_flags_t) String() string

type NXMouseButton

type NXMouseButton int64
const (
	NX_OneButton   NXMouseButton = 0
	NX_LeftButton  NXMouseButton = 1
	NX_RightButton NXMouseButton = 2
)

func (NXMouseButton) String

func (e NXMouseButton) String() string

type Os_clockid_t

type Os_clockid_t int64
const (
	OS_CLOCK_MACH_ABSOLUTE_TIME Os_clockid_t = 32
)

func (Os_clockid_t) String

func (e Os_clockid_t) String() string

type PMPageToPaperMappingType

type PMPageToPaperMappingType int64
const (
	KPMPageToPaperMappingNone       PMPageToPaperMappingType = 1
	KPMPageToPaperMappingScaleToFit PMPageToPaperMappingType = 2
)

func (PMPageToPaperMappingType) String

func (e PMPageToPaperMappingType) String() string

type Ptrauth_key

type Ptrauth_key int64
const (
	Ptrauth_key_none                     Ptrauth_key = -1
	Ptrauth_key_asia                     Ptrauth_key = 0
	Ptrauth_key_asib                     Ptrauth_key = 1
	Ptrauth_key_asda                     Ptrauth_key = 2
	Ptrauth_key_asdb                     Ptrauth_key = 3
	Ptrauth_key_process_independent_code Ptrauth_key = 0
	Ptrauth_key_process_dependent_code   Ptrauth_key = 1
	Ptrauth_key_process_independent_data Ptrauth_key = 2
	Ptrauth_key_process_dependent_data   Ptrauth_key = 3
	Ptrauth_key_return_address           Ptrauth_key = 1
	Ptrauth_key_frame_pointer            Ptrauth_key = 3
	Ptrauth_key_function_pointer         Ptrauth_key = 0
	Ptrauth_key_block_function           Ptrauth_key = 0
	Ptrauth_key_cxx_vtable_pointer       Ptrauth_key = 2
	Ptrauth_key_method_list_pointer      Ptrauth_key = 2
	Ptrauth_key_objc_isa_pointer         Ptrauth_key = 2
	Ptrauth_key_objc_super_pointer       Ptrauth_key = 2
	Ptrauth_key_objc_sel_pointer         Ptrauth_key = 3
	Ptrauth_key_objc_class_ro_pointer    Ptrauth_key = 2
	Ptrauth_key_block_descriptor_pointer Ptrauth_key = 2
	Ptrauth_key_init_fini_pointer        Ptrauth_key = 0
)

func (Ptrauth_key) String

func (e Ptrauth_key) String() string

type Qos_class_t

type Qos_class_t uint32
const (
	QOS_CLASS_USER_INTERACTIVE Qos_class_t = 33
	QOS_CLASS_USER_INITIATED   Qos_class_t = 25
	QOS_CLASS_DEFAULT          Qos_class_t = 21
	QOS_CLASS_UTILITY          Qos_class_t = 17
	QOS_CLASS_BACKGROUND       Qos_class_t = 9
	QOS_CLASS_UNSPECIFIED      Qos_class_t = 0
)

func (Qos_class_t) String

func (e Qos_class_t) String() string

type Virtual_memory_guard_exception_code_t

type Virtual_memory_guard_exception_code_t int64
const (
	KGUARD_EXC_DEALLOC_GAP                   Virtual_memory_guard_exception_code_t = 1
	KGUARD_EXC_RECLAIM_COPYIO_FAILURE        Virtual_memory_guard_exception_code_t = 2
	KGUARD_EXC_RECLAIM_INDEX_FAILURE         Virtual_memory_guard_exception_code_t = 4
	KGUARD_EXC_RECLAIM_DEALLOCATE_FAILURE    Virtual_memory_guard_exception_code_t = 8
	KGUARD_EXC_RECLAIM_ACCOUNTING_FAILURE    Virtual_memory_guard_exception_code_t = 9
	KGUARD_EXC_SEC_IOPL_ON_EXEC_PAGE         Virtual_memory_guard_exception_code_t = 10
	KGUARD_EXC_SEC_EXEC_ON_IOPL_PAGE         Virtual_memory_guard_exception_code_t = 11
	KGUARD_EXC_SEC_UPL_WRITE_ON_EXEC_REGION  Virtual_memory_guard_exception_code_t = 12
	KGUARD_EXC_LARGE_ALLOCATION_TELEMETRY    Virtual_memory_guard_exception_code_t = 13
	KGUARD_EXC_SEC_ACCESS_FAULT              Virtual_memory_guard_exception_code_t = 98
	KGUARD_EXC_SEC_ASYNC_ACCESS_FAULT        Virtual_memory_guard_exception_code_t = 99
	KGUARD_EXC_SEC_COPY_DENIED               Virtual_memory_guard_exception_code_t = 100
	KGUARD_EXC_SEC_SHARING_DENIED            Virtual_memory_guard_exception_code_t = 101
	KGUARD_EXC_MTE_SYNC_FAULT                Virtual_memory_guard_exception_code_t = 200
	KGUARD_EXC_MTE_ASYNC_USER_FAULT          Virtual_memory_guard_exception_code_t = 201
	KGUARD_EXC_MTE_ASYNC_KERN_FAULT          Virtual_memory_guard_exception_code_t = 202
	KGUARD_EXC_GUARD_OBJECT_ASYNC_USER_FAULT Virtual_memory_guard_exception_code_t = 203
	KGUARD_EXC_GUARD_OBJECT_ASYNC_KERN_FAULT Virtual_memory_guard_exception_code_t = 204
)

func (Virtual_memory_guard_exception_code_t) String

type Xpc_listener_create_flags_t

type Xpc_listener_create_flags_t int64
const (
	XPC_LISTENER_CREATE_NONE             Xpc_listener_create_flags_t = 0
	XPC_LISTENER_CREATE_INACTIVE         Xpc_listener_create_flags_t = 1
	XPC_LISTENER_CREATE_FORCE_MACH       Xpc_listener_create_flags_t = 2
	XPC_LISTENER_CREATE_FORCE_XPCSERVICE Xpc_listener_create_flags_t = 4
)

func (Xpc_listener_create_flags_t) String

type Xpc_session_create_flags_t

type Xpc_session_create_flags_t int64
const (
	XPC_SESSION_CREATE_NONE            Xpc_session_create_flags_t = 0
	XPC_SESSION_CREATE_INACTIVE        Xpc_session_create_flags_t = 1
	XPC_SESSION_CREATE_MACH_PRIVILEGED Xpc_session_create_flags_t = 2
)

func (Xpc_session_create_flags_t) String

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL