libobjc.A.dylib  objc_retain + 8  arrow_right  1 ContextKitExtraction  +[CKContextContentProviderUIScene _bestVisibleStringForView:usingExecutor:] + 1320  2 ContextKitExtraction  +[CKContextContentProviderUIScene _donateContentsOfWindow:usingExecutor:withOptions:] + 608  3 ContextKitExtraction  __78+[CKContextContentProviderUIScene extractFromScene:usingExecutor:withOptions:]_block_invoke + 72  4 ContextKitExtraction  __64-[CKContextExecutor addWorkItemToQueue:withWorkItem:andContext:]_block_invoke + 76  5 libdispatch.dylib  _dispatch_call_block_and_release + 32  6 libdispatch.dylib  _dispatch_client_callout + 20  7 libdispatch.dylib  _dispatch_main_queue_drain + 1020  8 libdispatch.dylib  _dispatch_main_queue_callback_4CF + 44  9 CoreFoundation  CFRUNLOOP_IS_SERVICING_THE_MAIN_DISPATCH_QUEUE + 16  10 CoreFoundation  __CFRunLoopRun + 2532  11 CoreFoundation  CFRunLoopRunSpecific + 600  12 GraphicsServices  GSEventRunModal + 164  13 UIKitCore  -[UIApplication _run] + 1100  14 UIKitCore  UIApplicationMain + 364  15 PDFReaderPro Free  main.m - Line 31  main + 31

Hello, is there a possibility to use the actionClassifier in CreateML ro create a fitnessApp that can recognize the action AND GIVE CORRECTION feedbacks to the user by using the the recognized keypoints? Maybe 3 keypoints as an angle and give feedback? How can I access those joints in Xcode?

Hi I have been the following WWDC21 "dynamic training on iOS" - I have been able to get the training working, with an output of the iterations etc being printed out in the console as training progresses. However I am unable to retrieve the checkpoints or result/model once training has completed (or is in progress) nothing in the callback fires. If I try to create a model from the sessionDirectory - it returns nil (even though training has clearly completed). Please can someone help or provide pointers on how to access the results/checkpoints so that I can make a MlModel and use it. var subscriptions = [AnyCancellable]()         let job = try! MLStyleTransfer.train(trainingData: datasource, parameters: trainingParameters, sessionParameters: sessionParameters) job.result.sink { result in             print("result ", result)         }         receiveValue: { model in try? model.write(to: sessionDirectory)             let compiledURL = try? MLModel.compileModel(at: sessionDirectory)             let mlModel = try? MLModel(contentsOf: compiledURL!)         }         .store(in: &subscriptions) This also does not work: job.checkpoints.sink { checkpoint in // Process checkpoint  let model = MLStyleTransfer(trainingData: checkpoint) } .store(in: &subscriptions)         } This is the printout in the console: Using CPU to create model +--------------+--------------+--------------+--------------+--------------+ | Iteration    | Total Loss   | Style Loss   | Content Loss | Elapsed Time | +--------------+--------------+--------------+--------------+--------------+ | 1            | 64.9218      | 54.9499      | 9.97187      | 3.92s        | 2022-02-20 15:14:37.056251+0000 DynamicStyle[81737:9175431] [ServicesDaemonManager] interruptionHandler is called. -[FontServicesDaemonManager connection]_block_invoke | 2            | 61.7283      | 24.6832      | 8.30343      | 9.87s        | | 3            | 59.5098      | 27.7834      | 11.7603      | 16.19s       | | 4            | 56.2737      | 16.163       | 10.985       | 22.35s       | | 5            | 53.0747      | 12.2062      | 12.0783      | 28.08s       | +--------------+--------------+--------------+--------------+--------------+ Any help would be appreciated on how to retrieve models. Thanks

arabic fonts on ios 15 it very bad :( Many Arabs did not like it.. I hope the developers use ios 14 arabic fonts .

I followed Apple's guidance in their articles Creating an Action Classifier Model, Gathering Training Videos for an Action Classifier, and Building an Action Classifier Data Source. With this Core ML model file now imported in Xcode, how do use it to classify video frames? For each video frame I call do { let requestHandler = VNImageRequestHandler(cmSampleBuffer: sampleBuffer) try requestHandler.perform([self.detectHumanBodyPoseRequest]) } catch { print("Unable to perform the request: \(error.localizedDescription).") } But it's unclear to me how to use the results of the VNDetectHumanBodyPoseRequest which come back as the type [VNHumanBodyPoseObservation]?. How would I feed to the results into my custom classifier, which has an automatically generated model class TennisActionClassifier.swift? The classifier is for making predictions on the frame's body poses, labeling the actions as either playing a rally/point or not playing.

Fatal Exception: NSGenericException *** Collection <__NSArrayM: 0x28313ce10> was mutated while being enumerated. -[CAMPriorityNotificationCenter _removeObserver:fromObserversByName:] keyboard_arrow_down Fatal Exception: NSGenericException 0 CoreFoundation 0x1878e8298 __exceptionPreprocess 1 libobjc.A.dylib 0x19b642480 objc_exception_throw 2 CoreFoundation 0x1878e7c5c -[__NSSingleObjectEnumerator initWithObject:collection:] 3 CameraUI 0x1affb7e7c -[CAMPriorityNotificationCenter _removeObserver:fromObserversByName:] 4 CameraUI 0x1affb81a8 -[CAMPriorityNotificationCenter removeObserver:] 5 CameraUI 0x1b0066510 -[CAMCaptureEngine dealloc] 6 libsystem_blocks.dylib 0x1cfcbc784 _Block_release 7 libdispatch.dylib 0x18750a290 _dispatch_source_handler_dispose 8 libdispatch.dylib 0x18750935c _dispatch_source_invoke$VARIANT$armv81 9 libdispatch.dylib 0x1874fc210 _dispatch_lane_serial_drain$VARIANT$armv81 10 libdispatch.dylib 0x1874fce2c _dispatch_lane_invoke$VARIANT$armv81 11 libdispatch.dylib 0x18750666c _dispatch_workloop_worker_thread 12 libsystem_pthread.dylib 0x1cfd355bc _pthread_wqthread 13 libsystem_pthread.dylib 0x1cfd3886c start_wqthread Crashed: com.google.firebase.crashlytics.ios.exception SIGABRT ABORT 0x00000001b36927b0 FIRCLSProcessRecordAllThreads keyboard_arrow_down

In a section of my app I would like to recommend restaurants to users based on certain parameters. Some parameters have a higher weighting than others. In this WWDC Video a very similar app is made. Here if a user likes a dish a value of 1.0 is assigned to those specific keywords (that apple to the dish) with a value of -1.0 to all other keywords that don't apply to that dish. For my app if the user has ordered I then apply a value of 1.0 (to the keywords that apply) but if a user has just expressed interest (but not ordered) then can I apply a value of 0.5 (and -0.5) instead, would the model adapt to this?

Hi, is it possible to get the code for the demo app used in this presentation for the dynamic style transfer example please? thanks

I have problems when viewing an App on an iPad, it distorts the image, that is, the size. The App looks good on the iPhone. Thank you for your support.

Hi Team, We are seeing a strange issue on the iPad device with iOS v14.6 where our backend API is not getting invoked. We have verified the same API calling code on multiple iPhone devices & simulators with different iOS versions ranging from v13.0-v14.6 and on iPad simulators with iOS versions ranging from v14.0-v14.5. It seems to be working fine on all except the real iPad device with v14.6. Any help in these is really appreciated.

Hi everyone! In my app I need to re-train my MLRecommendation model everyday based on user data. Can I use Create ML directly from iOS or how to use Core ML for this task?

Anyone got Universal Controller working yet? Just updated to 15.3 beta (iPad, iMac and MacBook) still can’t seem to get it to work.

Hello! I was wondering if it would be possible for the sample code for the Meal App to be posted. There are some things I'd like to see regarding MLLinearRegressor and how models can be personalized with context and data.

it just said “try again later” and I couldn’t reinstall it

I'm running my iOS app on my Macbook with M1 cpu.I need to determine whether the current device is a Mac or iOS device...