Can access to SoundAnalysis (sound classifier built into next version of MacOS, iOS, WatchOS) be provided to my app running in the background on iPhone or Apple Watch? I want to monitor local sounds from Apple Watch and iPhones and take remote action for out of band data (ie. send alert to caregiver if coughing rate is too high, or if someone is knocking on the door for more than a minute, etc.)

I am working on the neural network classifier provided on the coremltools.readme.io in the updatable->neural network section(https://coremltools.readme.io/docs/updatable-neural-network-classifier-on-mnist-dataset). I am using the same code but I get an error saying that the coremltools.converters.keras.convert does not exist. But this I know can be coreml version issue. Right know I am using coremltools version 6.2. I converted this model to mlmodel with .convert only. It got converted successfully. But I face an error in the make_updatable function saying the loss layer must be softmax output. Even the coremlt package API reference there I found its because the layer name is softmaxND but it should be softmax. Now the problem is when I convert the model from Keras sequential model to coreml model. the layer name and type change. And the softmax changes to softmaxND. Does anyone faced this issue? if I execute this builder.inspect_layers(last=4) I get this output [Id: 32], Name: sequential/dense_1/Softmax (Type: softmaxND) Updatable: False Input blobs: ['sequential/dense_1/MatMul'] Output blobs: ['Identity'] [Id: 31], Name: sequential/dense_1/MatMul (Type: batchedMatmul) Updatable: False Input blobs: ['sequential/dense/Relu'] Output blobs: ['sequential/dense_1/MatMul'] [Id: 30], Name: sequential/dense/Relu (Type: activation) Updatable: False Input blobs: ['sequential/dense/MatMul'] Output blobs: ['sequential/dense/Relu'] In the make_updatable function when I execute builder.set_categorical_cross_entropy_loss(name='lossLayer', input='Identity') I get this error ValueError: Categorical Cross Entropy loss layer input (Identity) must be a softmax layer output.

Hey everyone, I've been updating my code to take advantage of the new Vision API for text recognition in macOS 15. I'm noticing some very odd behavior though, it seems like in general the new Vision API consistently produces worse results than the old API. For reference here is how I'm setting up my request. var request = RecognizeTextRequest() request.recognitionLevel = getOCRMode() // generally accurate request.usesLanguageCorrection = !disableLanguageCorrection // generally true request.recognitionLanguages = language.split(separator: ",").map { Locale.Language(identifier: String($0)) } // generally 'en' let observations = try? await request.perform(on: image) as [RecognizedTextObservation] Then I will process the results and just get the top candidate, which as mentioned above, typically is of worse quality then the same request formed with the old API. Am I doing something wrong here?

I am using Apple’s Vision framework with DetectHorizonRequest to detect the horizon in an image. Here is my code: func processHorizonImage(_ ciImage: CIImage) async { let request = DetectHorizonRequest() do { let result = try await request.perform(on: ciImage) print(result) } catch { print(error) } } After calling the perform method, I am getting result as nil. To ensure the request's correctness, I have verified the following: The input CIImage is valid and contains a visible horizon. No errors are being thrown. The relevant frameworks are properly imported. Given that my image contains a clear horizon, why am I still not getting any results? I would appreciate any help or suggestions to resolve this issue. Thank you for your support! This is the image

Hi All, Is it possible to record a video using the Object Capture instead of taking a series of pictures ? Is it possible to get the bounding box coordinates of the object we capture ?

Hello. I can't find anything about the SSML that is used in Apple's speech synthesis. SSML from Google, Amazon and W3C either don't work or work incorrectly. Where is Apple's documentation for their implementation of SSML?

hi, I am currently running LSTM on TensorFlow. However, when i switched from keras2 to keras3. code running time has increased 10 times -- it seems there is no GPU acceleration. Here is my code: batch size = 256 optimiser = adam activation = tanh _______________________________________________ Layer (type) Output Shape Param # ============================================= input_1 (InputLayer) [(None, 7, 16)] 0 bidirectional (Bidirection (None, 7, 320) 226560 al) bidirectional_1 (Bidirecti (None, 7, 512) 1181696 onal) bidirectional_2 (Bidirecti (None, 256) 656384 onal) dense (Dense) (None, 1) 257 ============================================== Total params: 2064897 (7.88 MB) Trainable params: 2064897 (7.88 MB) Non-trainable params: 0 (0.00 Byte) ______________________________________________ This is keras 3.6.0 + tensorflow 2.17.0 + tensorflow-metal 1.1.0 training status: Training------------ Epoch 1/200 28/681 ━━━━━━━━━━━━━━━━━━━━ 8:13 756ms/step - loss: 0.5901 - mape: 338.6876 - mse: 0.8591 This is keras 2.14.0 + tensorflow 2.14.0 + tensorflow-metal 1.1.0 training status: Training------------ Epoch 1/200 681/681 [==============================] - 37s 49ms/step - loss: 3.6345 - mape: 499038.7500 - mse: 34.4148 - val_loss: 3.5452 - val_mape: 41.7964 - val_mse: 32.0133 - lr: 0.0010 Is that because keras3 has no GPU support on macos? Apart from that, if I change LSTM activation from tanh to sigmoid in keras2, it does not have GPU support as well. My system is 15.0.1 and the code was running on python3.11 I am not sure why these happen. Thanks

what am I not understanding here. in short the view loads text from the jsons descriptions and then should filter out the words. and return and display a list of most used words, debugging shows words being identified by the code but does not filter them out private func loadWordCounts() { DispatchQueue.global(qos: .background).async { let fileManager = FileManager.default guard let documentsDirectory = try? fileManager.url(for: .documentDirectory, in: .userDomainMask, appropriateFor: nil, create: false) else { return } let descriptions = loadDescriptions(fileManager: fileManager, documentsDirectory: documentsDirectory) var counts = countWords(in: descriptions) let tagsToRemove: Set<NLTag> = [ .verb, .pronoun, .determiner, .particle, .preposition, .conjunction, .interjection, .classifier ] for (word, _) in counts { let tagger = NLTagger(tagSchemes: [.lexicalClass]) tagger.string = word let (tag, _) = tagger.tag(at: word.startIndex, unit: .word, scheme: .lexicalClass) if let unwrappedTag = tag, tagsToRemove.contains(unwrappedTag) { counts[word] = 0 } } DispatchQueue.main.async { self.wordCounts = counts } } }

What are the major differences in review process for AI based apps vis a vis normal apps for Apple store?

Where can I find an example of using this MPSGraph function? I'm trying to use it to paste an image into a larger canvas at certain coordinates. func sliceUpdateDataTensor( _ dataTensor: MPSGraphTensor, update updateTensor: MPSGraphTensor, starts: [NSNumber], ends: [NSNumber], strides: [NSNumber], startMask: UInt32, endMask: UInt32, squeezeMask: UInt32, name: String? ) -> MPSGraphTensor

Hi all, When executing an HLO program using the JAX metal PJRT plugin, the program fails due to an unsupported data type returned by the rng_bit_generator operation. The generated HLO includes: %output_state, %output = "mhlo.rng_bit_generator"(%1) <{rng_algorithm = #mhlo.rng_algorithm<PHILOX>}> : (tensor<3xi64>) -> (tensor<3xi64>, tensor<3xui32>) The error message indicates that: Metal only supports MPSDataTypeFloat16, MPSDataTypeBFloat16, MPSDataTypeFloat32, MPSDataTypeInt32, and MPSDataTypeInt64. The use of ui32 seems to be incompatible with Metal’s allowed types. I’m trying to understand if the ui32 output is the problem or maybe the use of rng_bit_generator is wrong. Could you clarify if there is a workaround or planned support for ui32 output in this context? Alternatively, guidance on configuring rng_bit_generator for compatibility with Metal’s supported types would be greatly appreciated.

Submited as : FB16052050 I am looking to adopt Machine Learning in a more granular manner, going beyond just using pre-built Metal, Core ML, or Create ML approaches. Specifically, I want to train models using Open Python PyTorch libraries, as these offer greater flexibility compared to Apple's native tools. However, these PyTorch APIs are primarily optimised for NVIDIA GPUs (or TPUs), not Apple's M3 or Apple Neural Engine (ANE). My goal is to train the models locally without resorting to cloud-based solutions for training or inference, and to then convert the models into Core ML format for deployment on Apple hardware. This would allow me to leverage Apple's hardware acceleration (via ANE, Metal, and MPS) while maintaining control over the training process in PyTorch. I want to know: What are my options for training models in PyTorch on local hardware (Apple M3 or equivalent), and how can I ensure that the PyTorch model can eventually be converted to Core ML without losing flexibility in model training and customisation? How can I perform training in PyTorch and avoid being restricted to inference-only workflows as Core ML typically allows? Is it possible to use the training capabilities of PyTorch and still get the performance benefits of Apple's hardware for both training and inference? What are the best practices or tools to ensure that my training pipeline in PyTorch is compatible with Apple's hardware constraints and optimised for local execution? I'm seeking a practical, cloud-free approach on Apple Hardware only that allows me to train models in PyTorch (keeping control over the training process) while ensuring that they can be deployed efficiently using Core ML on Apple hardware.

Hello all, I'm working on a project that involves listening to a person speak off of a script and I want to stop then restart the recognitionTask between sections so I don't run afoul of keeping the recognitionTask running for longer than it needs to. Also, I'd like to be able to flush the current input between sections so the input from the previous section doesn't roll over into the next one. This is based on the sample code for SFSpeechRecognizer so there's a chance I might be misunderstanding something. private func restartRecording() { let inputNode = audioEngine.inputNode audioEngine.stop() inputNode.removeTap(onBus: 0) recognitionRequest?.endAudio() recordingStarted = false recognitionTask?.cancel() do { try startRecording() } catch { print("Oopsie.") } } Here's my code. When I run it, the recognition task doesn't restart. Any ideas?

I'm trying to build llama.cpp, a popular tool for running LLMs locally on macos15.1.1 (24B91) Sonoma using cmake but am encountering errors. Here is the stack overflow post regarding the issue: https://stackoverflow.com/questions/79304015/cmake-unable-to-find-foundation-framework-on-macos-15-1-1-24b91?noredirect=1#comment139853319_79304015

I am attempting to install Tensorflow on my M1 and I seem to be unable to find the correct matching versions of jax, jaxlib and numpy to make it all work. I am in Bash, because the default shell gave me issues. I downgraded to python 3.10, because with 3.13, I could not do anything right. Current actions: bash-3.2$ python3.10 -m venv ~/venv-metal bash-3.2$ python --version Python 3.10.16 python3.10 -m venv ~/venv-metal source ~/venv-metal/bin/activate python -m pip install -U pip python -m pip install tensorflow-macos And here, I keep running tnto errors like: (venv-metal):~$ pip install tensorflow-macos tensorflow-metal ERROR: Could not find a version that satisfies the requirement tensorflow-macos (from versions: none) ERROR: No matching distribution found for tensorflow-macos What is wrong here? How can I fix that? It seems like the system wants to use the x86 version of python ... which can't be right.

Hi everyone, I'm working with VNFeaturePrintObservation in Swift to compute the similarity between images. The computeDistance function allows me to calculate the distance between two images, and I want to cluster similar images based on these distances. Current Approach Right now, I'm using a brute-force approach where I compare every image against every other image in the dataset. This results in an O(n^2) complexity, which quickly becomes a bottleneck. With 5000 images, it takes around 10 seconds to complete, which is too slow for my use case. Question Are there any efficient algorithms or data structures I can use to improve performance? If anyone has experience with optimizing feature vector clustering or has suggestions on how to scale this efficiently, I'd really appreciate your insights. Thanks!

Hello, I am thinking of buying the MacBook Pro 14" with M4 Pro for ML/AI/ NLP tasks mostly. And since I have only used Windows before, I am wandering if it is compatible with libraries like "Pytorch" and "TensorFlow" etc., or people have experienced problems in installation... Thank you!

I'm implementing an LLM with Metal Performance Shader Graph, but encountered a very strange behavior, occasionally, the model will report an error message as this: LLVM ERROR: SmallVector unable to grow. Requested capacity (9223372036854775808) is larger than maximum value for size type (4294967295) and crash, the stack backtrace screenshot is attached. Note that 5th frame is mlir::getIntValues<long long> and 6th frame is llvm::SmallVectorBase<unsigned int>::grow_pod It looks like mlir mistakenly took a 64 bit value for a 32 bit type. Unfortunately, I could not found the source code of mlir::getIntValues, maybe it's Apple's closed source fork of llvm for MPS implementation? Anyway, any opinion or suggestion on that?

In an under-development MacOS & iOS app, I need to identify various measurements from OCR'ed text: length, weight, counts per inch, area, percentage. The unit type (e.g. UnitLength) needs to be identified as well as the measurement's unit (e.g. .inches) in order to convert the measurement to the app's internal standard (e.g. centimetres), the value of which is stored the relevant CoreData entity. The use of NLTagger and NLTokenizer is problematic because of the various representations of the measurements: e.g. "50g.", "50 g", "50 grams", "1 3/4 oz." Currently, I use a bespoke algorithm based on String contains and step-wise evaluation of characters, which is reasonably accurate but requires frequent updating as further representations are detected. I'm aware of the Python SpaCy model being capable of NER Measurement recognition, but am reluctant to incorporate a Python-based solution into a production app. (ref [https://developer.apple.com/forums/thread/30092]) My preference is for an open-source NER Measurement model that can be used as, or converted to, some form of a Swift compatible Machine Learning model. Does anyone know of such a model?

Incident Identifier: 4C22F586-71FB-4644-B823-A4B52D158057 CrashReporter Key: adc89b7506c09c2a6b3a9099cc85531bdaba9156 Hardware Model: Mac16,10 Process: PRISMLensCore [16561] Path: /Applications/PRISMLens.app/Contents/Resources/app.asar.unpacked/node_modules/core-node/PRISMLensCore.app/PRISMLensCore Identifier: com.prismlive.camstudio Version: (null) ((null)) Code Type: ARM-64 Parent Process: ? [16560] Date/Time: (null) OS Version: macOS 15.4 (24E5228e) Report Version: 104 Exception Type: EXC_CRASH (SIGABRT) Exception Codes: 0x00000000 at 0x0000000000000000 Crashed Thread: 34 Application Specific Information: *** Terminating app due to uncaught exception 'NSInvalidArgumentException', reason: '*** -[__NSArrayM insertObject:atIndex:]: object cannot be nil' Thread 34 Crashed: 0 CoreFoundation 0x000000018ba4dde4 0x18b960000 + 974308 (__exceptionPreprocess + 164) 1 libobjc.A.dylib 0x000000018b512b60 0x18b4f8000 + 109408 (objc_exception_throw + 88) 2 CoreFoundation 0x000000018b97e69c 0x18b960000 + 124572 (-[__NSArrayM insertObject:atIndex:] + 1276) 3 Portrait 0x0000000257e16a94 0x257da3000 + 473748 (-[PTMSRResize addAdditionalOutput:] + 604) 4 Portrait 0x0000000257de91c0 0x257da3000 + 287168 (-[PTEffectRenderer initWithDescriptor:metalContext:useHighResNetwork:faceAttributesNetwork:humanDetections:prevTemporalState:asyncInitQueue:sharedResources:] + 6204) 5 Portrait 0x0000000257dab21c 0x257da3000 + 33308 (__33-[PTEffect updateEffectDelegate:]_block_invoke.241 + 164) 6 libdispatch.dylib 0x000000018b739b2c 0x18b738000 + 6956 (_dispatch_call_block_and_release + 32) 7 libdispatch.dylib 0x000000018b75385c 0x18b738000 + 112732 (_dispatch_client_callout + 16) 8 libdispatch.dylib 0x000000018b742350 0x18b738000 + 41808 (_dispatch_lane_serial_drain + 740) 9 libdispatch.dylib 0x000000018b742e2c 0x18b738000 + 44588 (_dispatch_lane_invoke + 388) 10 libdispatch.dylib 0x000000018b74d264 0x18b738000 + 86628 (_dispatch_root_queue_drain_deferred_wlh + 292) 11 libdispatch.dylib 0x000000018b74cae8 0x18b738000 + 84712 (_dispatch_workloop_worker_thread + 540) 12 libsystem_pthread.dylib 0x000000018b8ede64 0x18b8eb000 + 11876 (_pthread_wqthread + 292) 13 libsystem_pthread.dylib 0x000000018b8ecb74 0x18b8eb000 + 7028 (start_wqthread + 8)