Struct MLPredictionOptions

Source

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

Available on crate feature MLPredictionOptions only.

Expand description

MLPredictionOptions

An object to hold options / controls / parameters of how model prediction is performed

Implementations§

Source §

impl MLPredictionOptions

Source

pub unsafe fn usesCPUOnly(&self) -> bool

👎Deprecated

Set to YES to force computation to be on the CPU only

Source

pub unsafe fn setUsesCPUOnly(&self, uses_cpu_only: bool)

👎Deprecated

Setter for usesCPUOnly.

Source

pub unsafe fn outputBackings( &self, ) -> Retained<NSDictionary<NSString, AnyObject>>

Propose the model to use the specified backing objects for the output feature values.

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.

  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.
  }

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.

  #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); }
                                                                        ... ];

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.

Source

pub unsafe fn setOutputBackings( &self, output_backings: &NSDictionary<NSString, AnyObject>, )

Setter for outputBackings.

Source §

impl MLPredictionOptions

Methods declared on superclass NSObject.

Source

pub unsafe fn init(this: Allocated<Self>) -> Retained<Self>

Source

pub unsafe fn new() -> Retained<Self>

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`
    }
}