Struct MLComputePlan

Source

#[repr(C)]
pub struct MLComputePlan { /* private fields */ }

Available on crate feature MLComputePlan only.

Expand description

A class describing the plan for executing a model.

The application can use the plan to estimate the necessary cost and resources of the model before running the predictions.

// Load the compute plan of an ML Program model.
[MLComputePlan loadContentsOfURL:modelURL configuration:configuration completionHandler:^(MLComputePlan * _Nullable computePlan, NSError * _Nullable error) {
if (!computePlan) {
// Handle error.
return;
}
MLModelStructureProgram *program = computePlan.modelStructure.program;
if (!program) {
[NSException raise:NSInternalInconsistencyException format:
"
Unexpected model type."];
}

MLModelStructureFunction *mainFunction = program.functions["main"];
if (!mainFunction) {
[NSException raise:NSInternalInconsistencyException format:
"
Missing main function."];
}

NSArray
<MLModelStructureProgramOperation
*> *operations = mainFunction.block.operations;
for (MLModelStructureProgramOperation *operation in operations) {
// Get the compute device usage for the operation.
MLComputeDeviceUsage *computeDeviceUsage = [computePlan computeDeviceUsageForMLProgramOperation:operation];
// Get the estimated cost of executing the operation.
MLComputePlanCost *estimatedCost = [computePlan estimatedCostOfMLProgramOperation:operation];

}
}];

Implementations§

Source §

pub unsafe fn loadContentsOfURL_configuration_completionHandler( url: &NSURL, configuration: &MLModelConfiguration, handler: &DynBlock<dyn Fn(mut MLComputePlan, mut NSError)>, )

Available on crate features MLModelConfiguration and block2 only.

Construct the compute plan of a model asynchronously given the location of its on-disk representation.

Parameter url: The location of its on-disk representation (.mlmodelc directory).

Parameter configuration: The model configuration.

Parameter handler: When the compute plan is constructed successfully or unsuccessfully, the completion handler is invoked with a valid MLComputePlan instance or NSError object.

Source

pub unsafe fn loadModelAsset_configuration_completionHandler( asset: &MLModelAsset, configuration: &MLModelConfiguration, handler: &DynBlock<dyn Fn(mut MLComputePlan, mut NSError)>, )

Available on crate features MLModelAsset and MLModelConfiguration and block2 only.

Construct the compute plan of a model asynchronously given the model asset.

Parameter asset: The model asset.

Parameter configuration: The model configuration.

Parameter handler: When the compute plan is constructed successfully or unsuccessfully, the completion handler is invoked with a valid MLComputePlan instance or NSError object.

Source

pub unsafe fn estimatedCostOfMLProgramOperation( &self, operation: &MLModelStructureProgramOperation, ) -> Option<Retained<MLComputePlanCost>>

Available on crate features MLComputePlanCost and MLModelStructureProgramOperation only.

Returns the estimated cost of executing an ML Program operation.

Parameter operation: An ML Program operation.

Returns: The estimated cost of executing the operation or nil if the cost couldn’t be estimated.

Source

pub unsafe fn computeDeviceUsageForNeuralNetworkLayer( &self, layer: &MLModelStructureNeuralNetworkLayer, ) -> Option<Retained<MLComputePlanDeviceUsage>>

Available on crate features MLComputePlanDeviceUsage and MLModelStructureNeuralNetworkLayer only.

Returns the anticipated compute devices that would be used for executing a NeuralNetwork layer.

Parameter 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.

Source

pub unsafe fn computeDeviceUsageForMLProgramOperation( &self, operation: &MLModelStructureProgramOperation, ) -> Option<Retained<MLComputePlanDeviceUsage>>

Available on crate features MLComputePlanDeviceUsage and MLModelStructureProgramOperation only.

Returns The anticipated compute devices that would be used for executing an ML Program operation.

Parameter operation: An ML Program operation.

Returns: The anticipated compute devices that would be used for executing the operation or nilif the usage couldn’t be determined.

Source

pub unsafe fn modelStructure(&self) -> Retained<MLModelStructure>

Available on crate feature MLModelStructure only.

The model structure.

Methods from Deref<Target = NSObject>§

Source

pub fn doesNotRecognizeSelector(&self, sel: Sel) -> !

Handle messages the object doesn’t recognize.

See Apple’s documentation for details.

Methods from Deref<Target = AnyObject>§

Source

pub fn class(&self) -> &'static AnyClass

Dynamically find the class of this object.

§Panics

May panic if the object is invalid (which may be the case for objects returned from unavailable init/new methods).

§Example

Check that an instance of NSObject has the precise class NSObject.

use objc2::ClassType;
use objc2::runtime::NSObject;

let obj = NSObject::new();
assert_eq!(obj.class(), NSObject::class());

Source

pub unsafe fn get_ivar<T>(&self, name: &str) -> &T
where T: Encode,

👎Deprecated: this is difficult to use correctly, use Ivar::load instead.

Use Ivar::load instead.

§Safety

The object must have an instance variable with the given name, and it must be of type T.

See Ivar::load_ptr for details surrounding this.

Source

pub fn downcast_ref<T>(&self) -> Option<&T>
where T: DowncastTarget,

Attempt to downcast the object to a class of type T.

This is the reference-variant. Use Retained::downcast if you want to convert a retained object to another type.

§Mutable classes

Some classes have immutable and mutable variants, such as NSString and NSMutableString.

When some Objective-C API signature says it gives you an immutable class, it generally expects you to not mutate that, even though it may technically be mutable “under the hood”.

So using this method to convert a NSString to a NSMutableString, while not unsound, is generally frowned upon unless you created the string yourself, or the API explicitly documents the string to be mutable.

See Apple’s documentation on mutability and on isKindOfClass: for more details.

§Generic classes

Objective-C generics are called “lightweight generics”, and that’s because they aren’t exposed in the runtime. This makes it impossible to safely downcast to generic collections, so this is disallowed by this method.

You can, however, safely downcast to generic collections where all the type-parameters are AnyObject.

§Panics

This works internally by calling isKindOfClass:. That means that the object must have the instance method of that name, and an exception will be thrown (if CoreFoundation is linked) or the process will abort if that is not the case. In the vast majority of cases, you don’t need to worry about this, since both root objects NSObject and NSProxy implement this method.

§Examples

Cast an NSString back and forth from NSObject.

use objc2::rc::Retained;
use objc2_foundation::{NSObject, NSString};

let obj: Retained<NSObject> = NSString::new().into_super();
let string = obj.downcast_ref::<NSString>().unwrap();
// Or with `downcast`, if we do not need the object afterwards
let string = obj.downcast::<NSString>().unwrap();

Try (and fail) to cast an NSObject to an NSString.

use objc2_foundation::{NSObject, NSString};

let obj = NSObject::new();
assert!(obj.downcast_ref::<NSString>().is_none());

Try to cast to an array of strings.

use objc2_foundation::{NSArray, NSObject, NSString};

let arr = NSArray::from_retained_slice(&[NSObject::new()]);
// This is invalid and doesn't type check.
let arr = arr.downcast_ref::<NSArray<NSString>>();

This fails to compile, since it would require enumerating over the array to ensure that each element is of the desired type, which is a performance pitfall.

Downcast when processing each element instead.

use objc2_foundation::{NSArray, NSObject, NSString};

let arr = NSArray::from_retained_slice(&[NSObject::new()]);

for elem in arr {
    if let Some(data) = elem.downcast_ref::<NSString>() {
        // handle `data`
    }
}