How reliable is the Models, to use as a comparison, such as a cholesterol test, to inform, for example, whether it is worth it to go see a doctor? I would like to use Tool to attach the simple blood test data to the session and with this the Model can analyse and made a simple suggestion if is necessary to see a doctor etc.. ? ps.: Local model

From tensorflow-metal example: Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: ) I know that Apple silicon uses UMA, and that memory copies are typical of CUDA, but wouldn't the GPU memory still be faster overall? I have an iMac Pro with a Radeon Pro Vega 64 16 GB GPU and an Intel iMac with a Radeon Pro 5700 8 GB GPU. But using tensorflow-metal is still WAY faster than using the CPUs. Thanks for that. I am surprised the 5700 is twice as fast as the Vega though.

I've downloaded the Xcode-beta and run the sample project "FoundationModelsTripPlanner" but I got this error when trying generate the response. InferenceError::inferenceFailed::Error Domain=com.apple.UnifiedAssetFramework Code=5000 "There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.modelcatalog" UserInfo={NSLocalizedFailureReason=There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.modelcatalog} Device: M1 Pro Question: Is it because M1 not supporting this feature?

Does the Foundation Model provide Objective-C compatible APIs?

It appears that there is a size limit when training the Tabular Classification model in CreatML. When the training data is small, the training process completes smoothly after a specified period. However, as the data volume increases, the following issues occur: initially, the training process indicates that it is in progress, but after approximately 24 hours, it is automatically terminated after an hour. I am certain that this is not a manual termination by myself or others, but rather an automatic termination by the machine. This issue persists despite numerous attempts, and the only message displayed is “Training Canceled.” I would appreciate it if someone could explain the reason behind this behavior and provide a solution. Thank you for your assistance.

Hi everyone, I'm working on integrating object recognition from live video feeds into my existing app by following Apple's sample code. My original project captures video and records it successfully. However, after integrating the Vision-based object detection components (VNCoreMLRequest), no detections occur, and the callback for the request is never triggered. To debug this issue, I’ve added the following functionality: Set up AVCaptureVideoDataOutput for processing video frames. Created a VNCoreMLRequest using my Core ML model. The video recording functionality works as expected, but no object detection happens. I’d like to know: How to debug this further? Which key debug points or logs could help identify where the issue lies? Have I missed any key configurations? Below is a diff of the modifications I’ve made to my project for the new feature. Diff of Changes: (Attach the diff provided above) Specific Observations: The captureOutput method is invoked correctly, but there is no output or error from the Vision request callback. Print statements in my setup function setForVideoClassify() show that the setup executes without errors. Questions: Could this be due to issues with my Core ML model compatibility or configuration? Is the VNCoreMLRequest setup incorrect, or do I need to ensure specific image formats for processing? Platform: Xcode 16.1, iOS 18.1, Swift 5, SwiftUI, iPhone 11, Darwin MacBook-Pro.local 24.1.0 Darwin Kernel Version 24.1.0: Thu Oct 10 21:02:27 PDT 2024; root:xnu-11215.41.3~2/RELEASE_X86_64 x86_64 Any guidance or advice is appreciated! Thanks in advance.

When calling NLTagger.requestAssets with some languages, it hangs indefinitely both in the simulator and a device. This happens consistently for some languages like greek. An example call is NLTagger.requestAssets(for: .greek, tagScheme: .lemma). Other languages like french return immediately. I captured some logs from Console and found what looks like the repeated attempts to download the asset. I would expect the call to eventually terminate, either loading the asset or failing with an error.

This is my code: witch SystemLanguageModel.default.availability { case .available: ContentView() .popover(isPresented: $showSettings) { SettingsView().presentationCompactAdaptation(.popover) } case .unavailable(.modelNotReady): ContentUnavailableView("Apple Intelligence is unavailable", systemImage: "apple.intelligence.badge.xmark", description: Text("Please come back later.")) case .unavailable(.appleIntelligenceNotEnabled): ContentUnavailableView("Apple Intelligence is unavailable", systemImage: "apple.intelligence.badge.xmark", description: Text("Please turn on Apple Intelligence.")) case .unavailable(.deviceNotEligible): ContentUnavailableView("Apple Intelligence is unavailable", systemImage: "apple.intelligence.badge.xmark", description: Text("This device is not eligible for Apple Intelligence.")) case .unavailable: ContentUnavailableView("Apple Intelligence is unavailable", systemImage: "apple.intelligence.badge.xmark") } When I switch off Apple Intelligence, I expected "Please turn on Apple Intelligence.", but instead I get "Please come back later." This seems to be wrong error?

I get the following dyld error on an iPad Pro with Xcode 26 beta 4: Symbol not found: _$s16FoundationModels20LanguageModelSessionC7prewarm12promptPrefixyAA6PromptVSg_tF Any advice?

In WWDC25 Metal 4 released quite excited new features for machine learning optimization, but as we all know the pytorch based on metal shader performance (mps) is the one of most important tools for Mac machine learning area.but on mps introduced website we cannot see any support information for metal4.

Hello, I am developing an iOS app that uses machine learning models. To improve accuracy and user experience, I would like to download .mlmodel files (compiled and compressed as zip files) from our own server after the app is installed, and use them for inference within the app. No executable code, scripts, or dynamic libraries will be downloaded—only model data files are used. According to App Store Review Guideline 2.5.2, I understand that apps may not download or execute code which introduces or changes features or functionality. In this case, are compiled and zip-compressed .mlmodel files considered "data" rather than "code", and is it allowed to download and use them in the app? If there are any restrictions or best practices related to this, please let me know. Thank you.

I am experimenting with Foundation Models in my time tracking app to analyze users tracked events, but I am finding that the model struggles with even basic computation of time. Specifically converting from seconds to hours and minutes. To give just one example, when I prompt: "Convert 3672 seconds to hours, minutes, and seconds. Don't include the calculations in the resulting output" I get this: "3672 seconds is equal to 1 hour, 0 minutes, and 36 seconds". Which is clearly wrong - it should be 1 hour, 1 minute, and 12 seconds. Another issue that I saw a lot is that seconds were considered to be minutes, or that the hours were just completely off. What can I do to make the support for math better? Or is that just something that the model is not meant to be used for?

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.

Access to VisionPro cameras is required for a research project. The project is on mixed reality software development for healthcare applications in dentistry.

Greetings, Ive been exerimenting with the new Apple intelligence chat. I want to be able to use my custom LLM and I made that work (I can chat back and forward from the left panel with my server) but I cannot find out how to change the editor contents like chatgpt does. chatgpt is able to change the current editor and, seems like, all files in the pbx. I tried to catch the call with charles with no success. In the OpenIA platform docs it doesnt mention anything that could change the code shown. does anyone know how to achieve this? Is the apple intelliece documentation lacking this features and will it be completed soon? will this features even be open for developers?

Hey, When generating responses with structured output and non-streaming API, it sometimes takes 3s, sometimes 10-20s. I am firing that request subsequently while testing the app. Is this by design, or any place I can learn more about what contributes to such variation?

Hey, has anyone figured out how the “Persons” list in Genmoji/Playground actually works? I’ve had a strange experience so far. When I first got access during Beta 2, the list randomly included about 10–15 people, even though my photo library contains many more recognizable faces. To try fixing this, I started naming faces in the Photos app, hoping they’d be added to the Genmoji/Playground list, but nothing changed. Then, after updating to Beta 3, it added just 2–3 of the people I had named. Encouraged, I spent about an hour naming all the faces in my library. But a few hours later, the list unexpectedly removed around 10 people, leaving me with fewer than I had initially. I’ve also read that leaving the phone locked and plugged into power should help sort people in the library, but that hasn’t worked for me yet. Anyone else experienced this or found a way to make it work? Thanks!

I have a smallish image classifier I've been working on using the Create ML app. For a while everything was going fine, but lately, as the dataset has gotten larger, Create ML seems to stop during the testing phase with no error or test results. You can see here that there is no score in the result box, even though there are testing started and completed messages: No error message is shown in the Create ML app, but I do see these messages in the log: default 14:25:36.529887-0500 MLRecipeExecutionService [0x6000012bc000] activating connection: mach=false listener=false peer=false name=com.apple.coremedia.videodecoder default 14:25:36.529978-0500 MLRecipeExecutionService [0x41c5d34c0] activating connection: mach=false listener=true peer=false name=(anonymous) default 14:25:36.530004-0500 MLRecipeExecutionService [0x41c5d34c0] Channel could not return listener port. default 14:25:36.530364-0500 MLRecipeExecutionService [0x429a88740] activating connection: mach=false listener=false peer=true name=com.apple.xpc.anonymous.0x41c5d34c0.peer[1167].0x429a88740 default 14:25:36.534523-0500 MLRecipeExecutionService [0x6000012bc000] invalidated because the current process cancelled the connection by calling xpc_connection_cancel() default 14:25:36.534537-0500 MLRecipeExecutionService [0x41c5d34c0] invalidated because the current process cancelled the connection by calling xpc_connection_cancel() default 14:25:36.534544-0500 MLRecipeExecutionService [0x429a88740] invalidated because the current process cancelled the connection by calling xpc_connection_cancel() error 14:25:36.558788-0500 MLRecipeExecutionService CreateWithURL:342: *** ERROR: err=24 (Too many open files) - could not open '<CFURL 0x60000079b540 [0x1fdd32240]>{string = file:///Users/kevin/Library/Mobile%20Documents/com~apple~CloudDocs/Binary%20Formations/Under%20My%20Roof/Core%20ML%20Training%20Data/Household%20Items/Output/2025.01.23_12.55.16/Test/Stove/Test480.webp, encoding = 134217984, base = (null)}' default 14:25:36.559030-0500 MLRecipeExecutionService Error: <private> default 14:25:36.559077-0500 MLRecipeExecutionService Error: <private> Of particular interest is the "Too many open files" message from MLRecipeExecutionService referencing one of the test images. There are a total of 2,555 test images, which I wouldn't think would be a very large set. The system doesn't seem to be running out of memory or anything like that. Near the end of the test run there MLRecipeExecution service had 2934 file descriptors open according to lsof. Has anyone else run into this or know of a workaround? So far I've tried rebooting and recreating the Create ML project. Currently using Create ML Version 6.1 (150.3) on macOS 15.2 (24C101) running on a Mac Studio.

Hi Apple team, When using AppShortcutsProvider, I hit the hard limit: Each app may have at most 10 App Shortcuts. This feels limiting for apps that offer multiple workflows and would benefit from deeper Siri integration. Could this cap be raised — ideally to 30 — to support broader use of AppIntents, enhance Siri automation, and unlock more system-level capabilities? AppShortcuts are a fantastic tool. Increasing the limit would make them even more powerful. Thanks!

Hi all, I'm working on an app to classify dog breeds via CoreML, but when I try training a model using Image Feature Print v2, I get the following error: Failed to create CVPixelBufferPool. Width = 0, Height = 0, Format = 0x00000000 Strangely, when I switch back to Image Feature Print v1, the model trains perfectly fine. I've verified that there aren't any invalid or broken images in my dataset. Is there a fix for this? Thanks!