i believe i am encountering a bug in the MPS backend of CoreML. i believe there is an invalid conversion of a slice_by_index + gather operation resulting in indexing the wrong values on GPU execution. the following is a python program using the coremltools library illustrating the issue: from coremltools.converters.mil import Builder as mb from coremltools.converters.mil.mil import types dB = 20480 shapeI = (2, dB) shapeB = (dB, 22) @mb.program(input_specs=[mb.TensorSpec(shape=shapeI, dtype=types.int32), mb.TensorSpec(shape=shapeB)]) def prog(i, b): lslice = mb.slice_by_index(x=i, begin=[0, 0], end=[1, dB], end_mask=[False, True], squeeze_mask=[True, False], name='slice_left') rslice = mb.slice_by_index(x=i, begin=[1, 0], end=[2, dB], end_mask=[False, True], squeeze_mask=[True, False], name='slice_right') ldata = mb.gather(x=b, indices=lslice) rdata = mb.gather(x=b, indices=rslice) # actual bug in optimization of gather+slice x = mb.add(x=ldata, y=rdata) # dummy ops to make a bigger graph to run on GPU x = mb.mul(x=x, y=2.) x = mb.mul(x=x, y=.5) x = mb.mul(x=x, y=2.) x = mb.mul(x=x, y=.5) x = mb.mul(x=x, y=2.) x = mb.mul(x=x, y=.5) x = mb.mul(x=x, y=2.) x = mb.mul(x=x, y=.5) x = mb.mul(x=x, y=2.) x = mb.mul(x=x, y=.5) x = mb.mul(x=x, y=2.) x = mb.mul(x=x, y=.5) x = mb.mul(x=x, y=2.) x = mb.mul(x=x, y=.5) x = mb.mul(x=x, y=1., name='result') return x input_types = [ ct.TensorType(name="i", shape=shapeI, dtype=np.int32), ct.TensorType(name="b", shape=shapeB, dtype=np.float32), ] with tempfile.TemporaryDirectory() as tmpdirname: model_cpu = ct.convert(prog, inputs=input_types, compute_precision=ct.precision.FLOAT32, compute_units=ct.ComputeUnit.CPU_ONLY, package_dir=tmpdirname + 'model_cpu.mlpackage') model_gpu = ct.convert(prog, inputs=input_types, compute_precision=ct.precision.FLOAT32, compute_units=ct.ComputeUnit.CPU_AND_GPU, package_dir=tmpdirname + 'model_gpu.mlpackage') inputs = { "i": torch.randint(0, shapeB[0], shapeI, dtype=torch.int32), "b": torch.rand(shapeB, dtype=torch.float32), } cpu_output = model_cpu.predict(inputs) gpu_output = model_gpu.predict(inputs) # equivalent to prog expected = inputs["b"][inputs["i"][0]] + inputs["b"][inputs["i"][1]] # what actually happens on GPU actual = inputs["b"][inputs["i"][0]] + inputs["b"][inputs["i"][0]] print(f"diff expected vs cpu: {np.sum(np.absolute(expected - cpu_output['result']))}") print(f"diff expected vs gpu: {np.sum(np.absolute(expected - gpu_output['result']))}") print(f"diff actual vs gpu: {np.sum(np.absolute(actual - gpu_output['result']))}") the issue seems to occur in the slice_right + gather operations when executed on GPU. the wrong items in input "i" are selected. the program outpus diff expected vs cpu: 0.0 diff expected vs gpu: 150104.015625 diff actual vs gpu: 0.0 this behavior has been tested on MacBook Pro 14inches 2023, (M2 pro) on mac os 14.7, using coremltools 8.0b2 with python 3.9.19

VNRecognizeTextRequest2 did not recognize the upside down text of English text. VNRecognizeTextRequest3 can recognize the text even if English text is upside down. Till iOS 17, I can select VNRecognizeTextRequest2 or VNRecognizeTextRequest3 in my code which is minimum build is iOS16 when I need upside down text detection required.. But on iOS18, even if I set the VNRecognizeTextRequest2 in my code, result seems to be based on the VNRecognizeTextRequest3 because upside down text is detected. VNRecognizeTextRequest2 was deplicant on iOS18, I know. How can I recognize the observation result is upside down or not? Are there any solution with VNRecognizeTextRequest3?

The following code taken from keras.io produces the error InternalError: Exception encountered when calling GPT2Tokenizer.call(). ... 2 root error(s) found. (0) INTERNAL: stream cannot wait for itself Macos on Macbook, M2 Max. Setting the optimizer to "Adam" does not help. import keras_nlp # version 0.15 causal_lm = keras_nlp.models.GPT2CausalLM.from_preset("gpt2_base_en") causal_lm.compile(sampler="greedy") # the next call produces the error causal_lm.generate(["Keras is a"])

Where does the processing power to enact certain AI capabilities come from? Is it hosted on the originating device? Or does the device send contents of originating information to Apple assets to process and give product to end user? e.g. If I ask AI to summarize an email will it send the contents of the email to an Apple AI asset to process it and give the summary to the originating device.

I signed up for apple intelligence on my IPad Air m1 and then updated my phone today. It tells me that I’ve already been put on a waitlist i didn’t even join? And it’s been stuck on that for 2 days now

i have iphone 15 pro max on ios 18.1 I tried to join Apple Intelligence about three weeks ago, but I'm still stuck on the waitlist. I've already tried everything recommended by Apple, including changing my region and Siri's language to English (US). Can anyone help me figure out how to solve this issue?

Following this instruction to install jax (https://developer.apple.com/metal/jax/), I still encountered this error: RuntimeError: This version of jaxlib was built using AVX instructions, which your CPU and/or operating system do not support. This error is frequently encountered on macOS when running an x86 Python installation on ARM hardware. In this case, try installing an ARM build of Python. Otherwise, you may be able work around this issue by building jaxlib from source. How to fix it?

Xcode Version 16.0 (16A242d) iOS18 - Swift There seems to be a behavior change on iOS18 when using AppShortcuts and AppIntents to pass string parameters. After Siri prompts for a string property requestValueDialog, if the user makes a statement the string is passed. If the user's statement is a question, however, the string is not sent to the AppIntent and instead Siri attempts to answer that question. Example Code: struct MyAppNameShortcuts: AppShortcutsProvider { @AppShortcutsBuilder static var appShortcuts: [AppShortcut] { AppShortcut( intent: AskQuestionIntent(), phrases: [ "Ask \(.applicationName) a question", ] ) } } struct AskQuestionIntent: AppIntent { static var title: LocalizedStringResource = .init(stringLiteral: "Ask a question") static var openAppWhenRun: Bool = false static var parameterSummary: some ParameterSummary { Summary("Search for \(\.$query)") } @Dependency private var apiClient: MockApiClient @Parameter(title: "Query", requestValueDialog: .init(stringLiteral: "What would you like to ask?")) var query: String // perform is not called if user asks a question such as "What color is the moon?" in response to requestValueDialog // iOS 17, the same string is passed though @MainActor func perform() async throws -> some IntentResult & ProvidesDialog & ShowsSnippetView { print("Query is: \(query)") let queryResult = try await apiClient.askQuery(queryString: query) let dialog = IntentDialog( full: .init(stringLiteral: queryResult.answer), supporting: .init(stringLiteral: "The answer to \(queryResult.question) is...") ) let view = SiriAnswerView(queryResult: queryResult) return .result(dialog: dialog, view: view) } } Given the above mock code: iOS17: Hey Siri Ask (AppName) a question Siri responds "What would you like to ask?" Say "What color is the moon?" String of "What color is the moon?" is passed to the AppIntent iOS18: Hey Siri Ask (AppName) a question Siri responds "What would you like to ask?" Say "What color is the moon?" Siri answers the question "What color is the moon?" Follow above steps again and instead reply "Moon" "Moon" is passed to AppIntent Basically any interrogative string parameters seem to be intercepted and sent to Siri proper rather than the provided AppIntent in iOS 18

Yesterday after updating to iOS 18.1 I joined the Apple Intelligence waitlist on my iPhone 15 Pro. About an hour later I noticed that it had the message "Support for processing Apple Intelligence on device is downloading." A day later it is still displaying the same message. I have strong wi-fi, I'm plugged in to power with full battery, and there are 750gb available in storage. From what I have been able to find online, this isn't the typical user experience and that it probably isn't going to complete the process at this point. Any advice on how to proceed and get Apple Intelligence installed and working would be greatly appreciated.

I just updated to 18.1 beta 4 and the only AI features I can use are the new Siri and photo cleanup. The rest are unavailable. Apple intelligence takes up 589mb on my iphone

Hi, I'm trying to personalize the Detect animal poses in Vision example (WWDC 23). Detect animal poses in Vision After some tests I saw that the landmarks and connection drawings work only if I do not ignore the safe area, if I ignore it (removing the toggle) or use the app on the iPad the drawings are no longer applied correctly. In the example GeometryReader is used to detect the size of the view: ... ZStack { GeometryReader { geo in AnimalSkeletonView(animalJoint: animalJoint, size: geo.size) } }.frame(maxWidth: .infinity) ... struct AnimalSkeletonView: View { // Get the animal joint locations. @StateObject var animalJoint = AnimalPoseDetector() var size: CGSize var body: some View { DisplayView(animalJoint: animalJoint) if animalJoint.animalBodyParts.isEmpty == false { // Draw the skeleton of the animal. // Iterate over all recognized points and connect the joints. ZStack { ZStack { // left head if let nose = animalJoint.animalBodyParts[.nose] { if let leftEye = animalJoint.animalBodyParts[.leftEye] { Line(points: [nose.location, leftEye.location], size: size) .stroke(lineWidth: 5.0) .fill(Color.orange) } } ... } } } } } // Create a transform that converts the pose's normalized point. struct Line: Shape { var points: [CGPoint] var size: CGSize func path(in rect: CGRect) -> Path { let pointTransform: CGAffineTransform = .identity .translatedBy(x: 0.0, y: -1.0) .concatenating(.identity.scaledBy(x: 1.0, y: -1.0)) .concatenating(.identity.scaledBy(x: size.width, y: size.height)) var path = Path() path.move(to: points[0]) for point in points { path.addLine(to: point) } return path.applying(pointTransform) } } Looking online I saw that it was recommended to change the property cameraView.previewLayer.videoGravity from: cameraView.previewLayer.videoGravity = .resizeAspectFill to: cameraView.previewLayer.videoGravity = .resizeAspect but it doesn't work for me. Could you help me understand where I'm wrong? Thanks!

hey just curious if apple intelligence will be available on iPhone 15 Plus as well??? in october or is there a way that iPhone 15 Plus owners can join apple intelligence’s wait lists or something??? please let me know !😫

I want my confidence of model is worked according to the when I detected the object by real time camera with help of ml model in android its gives me different results with different confidence as like 75, 40,30,95 not range 95 to 100 but when I used same model in ios its will give me range above 95 of any case. so what will be reason do you think

I need to add AI Image Playground in my iOS app with UIKit, as per WWDC 2024 introduce new AI Image Playground API, I didn't find any official document yet, So how can add it ?

Hello, I‘m using DockKit within my SwiftUI Application with GetStream. Before updating to iOS 18 yesterday the custom Tracking using DockKit worked like a charm, but After updating it stopped working unexpectedly. What‘s more curious: using the official GetStream Video Calls Application it works on iOS18 still, but Not within my Application. I can confirm, that my iPhone is still paired and I can receive logs about the current docking State and everything seems fine. Any suggestions what I‘m missing here?

As a user, when viewing a photo or image, I want to be able to tell Siri, “add this to ”, similar to example from the WWDC presentation where a photo is added to a note in the notes app. Is this... possible with app domains as they are documented? I see domains like open-file and open-photo, but I don't know if those are appropriate for this kind of functionality?

When I try to run basically any CoreML model using MLPredictionOptions.outputBackings , inference throws the following error: 2024-09-11 15:36:00.184740-0600 run_demo[4260:64822] [coreml] Unrecognized ANE execution priority (null) 2024-09-11 15:36:00.185380-0600 run_demo[4260:64822] *** Terminating app due to uncaught exception 'NSInvalidArgumentException', reason: 'Unrecognized ANE execution priority (null)' *** First throw call stack: ( 0 CoreFoundation 0x000000019812cec0 __exceptionPreprocess + 176 1 libobjc.A.dylib 0x0000000197c12cd8 objc_exception_throw + 88 2 CoreFoundation 0x000000019812cdb0 +[NSException exceptionWithName:reason:userInfo:] + 0 3 CoreML 0x00000001a1bf6504 _ZN12_GLOBAL__N_141espressoPlanPriorityFromPredictionOptionsEP19MLPredictionOptions + 264 4 CoreML 0x00000001a1bf68c0 -[MLNeuralNetworkEngine _matchEngineToOptions:error:] + 236 5 CoreML 0x00000001a1be254c __62-[MLNeuralNetworkEngine predictionFromFeatures:options:error:]_block_invoke + 68 6 libdispatch.dylib 0x0000000197e20658 _dispatch_client_callout + 20 7 libdispatch.dylib 0x0000000197e2fcd8 _dispatch_l *** Terminating app due to uncaught exception 'NSInvalidArgumentException', reason: 'Unrecognized ANE execution priority (null)' *** First throw call stack: ( 0 CoreFoundation 0x000000019812cec0 __exceptionPreprocess + 176 1 libobjc.A.dylib 0x0000000197c12cd8 objc_exception_throw + 88 2 CoreFoundation 0x000000019812cdb0 +[NSException exceptionWithName:reason:userInfo:] + 0 3 CoreML 0x00000001a1bf6504 _ZN12_GLOBAL__N_141espressoPlanPriorityFromPredictionOptionsEP19MLPredictionOptions + 264 4 CoreML 0x00000001a1bf68c0 -[MLNeuralNetworkEngine _matchEngineToOptions:error:] + 236 5 CoreML 0x00000001a1be254c __62-[MLNeuralNetworkEngine predictionFromFeatures:options:error:]_block_invoke + 68 6 libdispatch.dylib 0x0000000197e20658 _dispatch_client_callout + 20 7 libdispatch.dylib 0x0000000197e2fcd8 _dispatch_lane_barrier_sync_invoke_and_complete + 56 8 CoreML 0x00000001a1be2450 -[MLNeuralNetworkEngine predictionFromFeatures:options:error:] + 304 9 CoreML 0x00000001a1c9e118 -[MLDelegateModel _predictionFromFeatures:usingState:options:error:] + 776 10 CoreML 0x00000001a1c9e4a4 -[MLDelegateModel predictionFromFeatures:options:error:] + 136 11 libMLBackend_coreml.dylib 0x00000001002f19f0 _ZN6CoreML8runModelENS_5ModelERNSt3__16vectorIPvNS1_9allocatorIS3_EEEES7_ + 904 12 libMLBackend_coreml.dylib 0x00000001002c56e8 _ZZN8ModelImp9runCoremlEPN2ML7Backend17ModelIoBindingImpEENKUlvE_clEv + 120 13 libMLBackend_coreml.dylib 0x00000001002c1e40 _ZNSt3__110__function6__funcIZN2ML4Util10WorkThread11runInThreadENS_8functionIFvvEEEEUlvE_NS_9allocatorIS8_EES6_EclEv + 40 14 libMLBackend_coreml.dylib 0x00000001002bc3a4 _ZZN2ML4Util10WorkThreadC1EvENKUlvE_clEv + 160 15 libMLBackend_coreml.dylib 0x00000001002bc244 _ZNSt3__114__thread_proxyB7v160006INS_5tupleIJNS_10unique_ptrINS_15__thread_structENS_14default_deleteIS3_EEEEZN2ML4Util10WorkThreadC1EvEUlvE_EEEEEPvSC_ + 52 16 libsystem_pthread.dylib 0x0000000197fd32e4 _pthread_start + 136 17 libsystem_pthread.dylib 0x0000000197fce0fc thread_start + 8 ) libc++abi: terminating due to uncaught exception of type NSException Interestingly, if I don't use MLPredictionOptions to set pre-allocated output backings, then inference appears to run as expected. A similar issue seems to have been discussed and fixed here: https://developer.apple.com/forums/thread/761649 , however I'm seeing this issue on a beta build that I downloaded today (Sept 11 2024). Will this be fixed? Any advice would be greatly appreciated. Thanks

I've got Apple AI working on my iPhone 15 pro max, SIRI 2.0 working as expected, however I don't seem to have the below options for Apple AI working / appearing. AI in mail AI in notes Clean up just stuck on downloading in photos Not sure if my setup is wrong or it's just not available for me yet

Hello everyone, I have a PyTorch model that outputs an image. I converted this model to CoreML using coremltools, and the resulting CoreML model can be used in my iOS project to perform inference using the MLModel's prediction function, which returns a result of type CVPixelBuffer. I want to avoid allocating memory every time I call the prediction function. Instead, I would like to use a pre-allocated buffer. I noticed that MLModel provides an overloaded prediction function that accepts an MLPredictionOptions object. This object has an outputBackings member, which allows me to pass a pre-allocated CVPixelBuffer. However, when I attempt to do this, I encounter the following error: Copy from tensor to pixel buffer (pixel_format_type: BGRA, image_pixel_type: BGR8, component_dtype: INT, component_pack: FMT_32) is not supported. Could someone point out what I might be doing wrong? How can I make MLModel use my pre-allocated CVPixelBuffer instead of creating a new one each time? Here is the Python code I used to convert the PyTorch model to CoreML, where I specified the color_layout as coremltools.colorlayout.BGR: def export_ml(model, resolution="640x360"): ml_path = f"model.mlpackage" print("exporting ml model") width, height = map(int, resolution.split('x')) img0 = torch.randn(1, 3, height, width) img1 = torch.randn(1, 3, height, width) traced_model = torch.jit.trace(model, (img0, img1)) input_shape = ct.Shape(shape=(1, 3, height, width)) output_type_img = ct.ImageType(name="out", scale=1.0, bias=[0, 0, 0], color_layout=ct.colorlayout.BGR) ml_model = ct.convert( traced_model, inputs=[input_type_img0, input_type_img1], outputs=[output_type_img] ) ml_model.save(ml_path) Here is the Swift code in my iOS project that calls the MLModel's prediction function: func prediction(image1: CVPixelBuffer, image2: CVPixelBuffer, model: MLModel) -> CVPixelBuffer? { let options = MLPredictionOptions() guard let outputBuffer = outputBacking else { fatalError("Failed to create CVPixelBuffer.") } options.outputBackings = ["out": outputBuffer] // Perform the prediction guard let prediction = try? model.prediction(from: RifeInput(img0: image1, img1: image2), options: options) else { Log.i("Failed to perform prediction") return nil } // Extract the result guard let cvPixelBuffer = prediction.featureValue(for: "out")?.imageBufferValue else { Log.i("Failed to get results from the model") return nil } return cvPixelBuffer } Here is the code I used to create the outputBacking: let attributes: [String: Any] = [ kCVPixelBufferCGImageCompatibilityKey as String: true, kCVPixelBufferCGBitmapContextCompatibilityKey as String: true, kCVPixelBufferWidthKey as String: Int(640), kCVPixelBufferHeightKey as String: Int(360), kCVPixelBufferIOSurfacePropertiesKey as String: [:] ] let status = CVPixelBufferCreate(kCFAllocatorDefault, 640, 360, kCVPixelFormatType_32BGRA, attributes as CFDictionary, &outputBacking) guard let outputBuffer = outputBacking else { fatalError("Failed to create CVPixelBuffer.") } Any help or guidance would be greatly appreciated! Thank you!

Hi, I have an existing app with AppEntities defined, that works on iOS16 and iOS17. The AppEntities also have EntityPropertyQuery defined, so they work as 'find intents'. I want to use the new @AssistantEntity on iOS18, while supporting the previous versions. What's the best way to do this? For e.g. I have a 'person' AppEntity: @available(iOS 16.0, macOS 13.0, watchOS 9.0, tvOS 16.0, *) struct CJLogAppEntity: AppEntity { static var defaultQuery = CJLogAppEntityQuery() .... } struct CJLogAppEntityQuery: EntityPropertyQuery { ... } How do I adopt this with @AssistantEntity(schema: .journal.entry) for iOS18, while maintaining compatibility with iOS16 and 17?