At WWDC25 we launched a new type of Lab event for the developer community - Group Labs. A Group Lab is a panel Q&A designed for a large audience of developers. Group Labs are a unique opportunity for the community to submit questions directly to a panel of Apple engineers and designers. Here are the highlights from the WWDC25 Group Lab for Machine Learning and AI Frameworks. What are you most excited about in the Foundation Models framework? The Foundation Models framework provides access to an on-device Large Language Model (LLM), enabling entirely on-device processing for intelligent features. This allows you to build features such as personalized search suggestions and dynamic NPC generation in games. The combination of guided generation and streaming capabilities is particularly exciting for creating delightful animations and features with reliable output. The seamless integration with SwiftUI and the new design material Liquid Glass is also a major advantage. When should I still bring my own LLM via CoreML? It's generally recommended to first explore Apple's built-in system models and APIs, including the Foundation Models framework, as they are highly optimized for Apple devices and cover a wide range of use cases. However, Core ML is still valuable if you need more control or choice over the specific model being deployed, such as customizing existing system models or augmenting prompts. Core ML provides the tools to get these models on-device, but you are responsible for model distribution and updates. Should I migrate PyTorch code to MLX? MLX is an open-source, general-purpose machine learning framework designed for Apple Silicon from the ground up. It offers a familiar API, similar to PyTorch, and supports C, C++, Python, and Swift. MLX emphasizes unified memory, a key feature of Apple Silicon hardware, which can improve performance. It's recommended to try MLX and see if its programming model and features better suit your application's needs. MLX shines when working with state-of-the-art, larger models. Can I test Foundation Models in Xcode simulator or device? Yes, you can use the Xcode simulator to test Foundation Models use cases. However, your Mac must be running macOS Tahoe. You can test on a physical iPhone running iOS 18 by connecting it to your Mac and running Playgrounds or live previews directly on the device. Which on-device models will be supported? any open source models? The Foundation Models framework currently supports Apple's first-party models only. This allows for platform-wide optimizations, improving battery life and reducing latency. While Core ML can be used to integrate open-source models, it's generally recommended to first explore the built-in system models and APIs provided by Apple, including those in the Vision, Natural Language, and Speech frameworks, as they are highly optimized for Apple devices. For frontier models, MLX can run very large models. How often will the Foundational Model be updated? How do we test for stability when the model is updated? The Foundation Model will be updated in sync with operating system updates. You can test your app against new model versions during the beta period by downloading the beta OS and running your app. It is highly recommended to create an "eval set" of golden prompts and responses to evaluate the performance of your features as the model changes or as you tweak your prompts. Report any unsatisfactory or satisfactory cases using Feedback Assistant. Which on-device model/API can I use to extract text data from images such as: nutrition labels, ingredient lists, cashier receipts, etc? Thank you. The Vision framework offers the RecognizeDocumentRequest which is specifically designed for these use cases. It not only recognizes text in images but also provides the structure of the document, such as rows in a receipt or the layout of a nutrition label. It can also identify data like phone numbers, addresses, and prices. What is the context window for the model? What are max tokens in and max tokens out? The context window for the Foundation Model is 4,096 tokens. The split between input and output tokens is flexible. For example, if you input 4,000 tokens, you'll have 96 tokens remaining for the output. The API takes in text, converting it to tokens under the hood. When estimating token count, a good rule of thumb is 3-4 characters per token for languages like English, and 1 character per token for languages like Japanese or Chinese. Handle potential errors gracefully by asking for shorter prompts or starting a new session if the token limit is exceeded. Is there a rate limit for Foundation Models API that is limited by power or temperature condition on the iPhone? Yes, there are rate limits, particularly when your app is in the background. A budget is allocated for background app usage, but exceeding it will result in rate-limiting errors. In the foreground, there is no rate limit unless the device is under heavy load (e.g., camera open, game mode). The system dynamically balances performance, battery life, and thermal conditions, which can affect the token throughput. Use appropriate quality of service settings for your tasks (e.g., background priority for background work) to help the system manage resources effectively. Do the foundation models support languages other than English? Yes, the on-device Foundation Model is multilingual and supports all languages supported by Apple Intelligence. To get the model to output in a specific language, prompt it with instructions indicating the user's preferred language using the locale API (e.g., "The user's preferred language is en-US"). Putting the instructions in English, but then putting the user prompt in the desired output language is a recommended practice. Are larger server-based models available through Foundation Models? No, the Foundation Models API currently only provides access to the on-device Large Language Model at the core of Apple Intelligence. It does not support server-side models. On-device models are preferred for privacy and for performance reasons. Is it possible to run Retrieval-Augmented Generation (RAG) using the Foundation Models framework? Yes, it is possible to run RAG on-device, but the Foundation Models framework does not include a built-in embedding model. You'll need to use a separate database to store vectors and implement nearest neighbor or cosine distance searches. The Natural Language framework offers simple word and sentence embeddings that can be used. Consider using a combination of Foundation Models and Core ML, using Core ML for your embedding model.

Did something change on face detection / Vision Framework on iOS 15? Using VNDetectFaceLandmarksRequest and reading the VNFaceLandmarkRegion2D to detect eyes is not working on iOS 15 as it did before. I am running the exact same code on an iOS 14 and iOS 15 device and the coordinates are different as seen on the screenshot? Any Ideas?

Hi, as showed in the course I created the PyTorch model sample and want to export / convert this model o a CoreML iOS Model using the coremltools. Input is a 224x224 image and output is a image classification (3 different classes) I am using coremltools for this with this code: import coremltools as ct modelml = ct.convert( scripted_model, inputs=[ct.ImageType(shape=(1,3,224,244))] ) I have a working iOS App code which performs with another model which was created using Microsoft Azure Vision. The PyTorch exported model is loaded and a prediction is performed, but I am getting this error: Foundation.MonoTouchException: Objective-C exception thrown. Name: NSInvalidArgumentException Reason: -[VNCoreMLFeatureValueObservation identifier]: unrecognized selector sent to instance 0x2805dd3b0 When I check the exported model with Xcode and compare it with another model which is working with the sample iOS App code (created and exported from Microsoft Azure) I can see that the input (for image classification using the device camera) seems ok and is equal, but the output is totally different. (see screenshots) The working model has two outputs: loss => Dictionary (String => Double) classLabel => String My exported model using coremltools just has one export: MultiArray(Float32) (name var_1620, I think this is the last feature layer output of the EfficentNetB2) How do I change my model or my coremltools export to get the correct output for the prediction ? I read the coreml documentation (https://coremltools.readme.io/docs/pytorch-conversion) and tried some GitHub samples. But I never get the correct output. How do I export the PyTorch model so that the output is correct and the prediction will work ? Best Marco

Hello, I posted an issue on the coremltools GitHub about my Core ML models not performing as well on iOS 17 vs iOS 16 but I'm posting it here just in case. TL;DR The same model on the same device/chip performs far slower (doesn't use the Neural Engine) on iOS 17 compared to iOS 16. Longer description The following screenshots show the performance of the same model (a PyTorch computer vision model) on an iPhone SE 3rd gen and iPhone 13 Pro (both use the A15 Bionic). iOS 16 - iPhone SE 3rd Gen (A15 Bioinc) iOS 16 uses the ANE and results in fast prediction, load and compilation times. iOS 17 - iPhone 13 Pro (A15 Bionic) iOS 17 doesn't seem to use the ANE, thus the prediction, load and compilation times are all slower. Code To Reproduce The following is my code I'm using to export my PyTorch vision model (using coremltools). I've used the same code for the past few months with sensational results on iOS 16. # Convert to Core ML using the Unified Conversion API coreml_model = ct.convert( model=traced_model, inputs=[image_input], outputs=[ct.TensorType(name="output")], classifier_config=ct.ClassifierConfig(class_names), convert_to="neuralnetwork", # compute_precision=ct.precision.FLOAT16, compute_units=ct.ComputeUnit.ALL ) System environment: Xcode version: 15.0 coremltools version: 7.0.0 OS (e.g. MacOS version or Linux type): Linux Ubuntu 20.04 (for exporting), macOS 13.6 (for testing on Xcode) Any other relevant version information (e.g. PyTorch or TensorFlow version): PyTorch 2.0 Additional context This happens across "neuralnetwork" and "mlprogram" type models, neither use the ANE on iOS 17 but both use the ANE on iOS 16 If anyone has a similar experience, I'd love to hear more. Otherwise, if I'm doing something wrong for the exporting of models for iOS 17+, please let me know. Thank you!

Note: I posted this to the feedback assistant but haven't gotten a response for 3months =( FB13482199 I am trying to train a large image classifier. I have a training run for ~300000 images. Each image has a folder and the file names within the folders are somewhat random. 381 classes. I am on an M2 Pro, Sonoma 14.0 running CreateML Version 5.0 (121.1). I would prefer not to pursue the pytorch/HF -> coremltools route. CreateML seems to consistently crash ~25000-30000 images in during the feature extraction phase with "Unexpected Error". It does not seem to be due to an out of memory issue. I am looking for some guidance since it seems impossible to debug why this is consistently crashing. My initial assumption was that it could be due to blank/corrupt files. I do not think that is the case. I also checked if there were any special characters in the data/folders. I wasn't able to go through all, but did try some programatic regex. Don't think this is the case either. I attached the sysdiagnose results in feedback assistant after the crash happened. I did notice when going into /var/logs there was some write issue saying that Mac had written too much to disk. Note: I also tried Xcode 15.2-beta this time and the associated CoreML version. My questions: How can I fix this? How should I go about debugging CreateML errors in the future? 'Unexpected Error' - where can I go about getting the exact createml logs on my device? This is far too broad of an error statement Please let me know. As a note, I did successfully train a past model on ~100000 images. I am planning to 10-15x that if this run is successful. Please help, spent a lot of time gathering the extra data and to date have been an occasional power user of createml. Haven't heard back from Apple since December =/. I assume I'm not the only one with this problem, so looking for any instructions to hands on debug and help others. Thx!

i'm trying to create an NLModel within a MessageFilterExtension handler. The code works fine in the main app, but when I try to use it in the extension it fails to initialize. Just this doesn't even work and gets the error below. Single line that fails. SMS_Classifier is the class xcode generated for my model. This line works fine in the main app. let mlModel = try SMS_Classifier(configuration: MLModelConfiguration()).model Error Unable to locate Asset for contextual word embedding model for local en. MLModelAsset: load failed with error Error Domain=com.apple.CoreML Code=0 "initialization of text classifier model with model data failed" UserInfo={NSLocalizedDescription=initialization of text classifier model with model data failed} Any ideas?

The What’s New in Create ML session in WWDC24 went into great depth with time-series forecasting models (beginning at: 15:14) and mentioned these new models, capabilities, and tools for iOS 18. So, far, all I can find is API documentation. I don’t see any other session in WWDC24 covering these new time-series forecasting Create ML features. Is there more substance/documentation on how to use these with Create ML? Maybe I am looking in the wrong place but I am fairly new with ML. Are there any food truck / donut shop demo/sample code like in the video? It is of great interest to get ahead of the curve on this within business applications that may take advantage of this with inventory / ordering data.

The Translation API introduced at Session 10117 is impressive, but limiting it to SwiftUI is restrictive. This API works great in the demo, but for more complex apps, it lacks flexibility because it is bound to SwiftUI Views. Please consider making it available in non-SwiftUI environments.

I'm playing with the new Vision API for iOS18, specifically with the new CalculateImageAestheticsScoresRequest API. When I try to perform the image observation request I get this error: internalError("Error Domain=NSOSStatusErrorDomain Code=-1 \"Failed to create espresso context.\" UserInfo={NSLocalizedDescription=Failed to create espresso context.}") The code is pretty straightforward: if let image = image { let request = CalculateImageAestheticsScoresRequest() Task { do { let cgImg = image.cgImage! let observations = try await request.perform(on: cgImg) let description = observations.description let score = observations.overallScore print(description) print(score) } catch { print(error) } } } I'm running it on a M2 using the simulator. Is it a bug? What's wrong?

iOS 18 App Intents while supporting iOS 17 Hello, I have an existing app that supports iOS 17. I already have three App Intents but would like to add some of the new iOS 18 app intents like ShowInAppSearchResultsIntent. However, I am having a hard time using #available or @available to limit this ShowInAppSearchResultsIntent to iOS 18 only while still supporting iOS 17. Obviously, the ShowInAppSearchResultsIntent needs to use @AssistantIntent which is iOS 18 only, so I mark that struct as @available(iOS 18, *). That works as expected. It is when I need to add this "SearchSnippetIntent" intent to the AppShortcutsProvider, that I begin to have trouble doing. See code below: struct SnippetsShortcutsAppShortcutsProvider: AppShortcutsProvider { @AppShortcutsBuilder static var appShortcuts: [AppShortcut] { //iOS 17+ AppShortcut(intent: SnippetsNewSnippetShortcutsAppIntent(), phrases: [ "Create a New Snippet in \(.applicationName) Studio", ], shortTitle: "New Snippet", systemImageName: "rectangle.fill.on.rectangle.angled.fill") AppShortcut(intent: SnippetsNewLanguageShortcutsAppIntent(), phrases: [ "Create a New Language in \(.applicationName) Studio", ], shortTitle: "New Language", systemImageName: "curlybraces") AppShortcut(intent: SnippetsNewTagShortcutsAppIntent(), phrases: [ "Create a New Tag in \(.applicationName) Studio", ], shortTitle: "New Tag", systemImageName: "tag.fill") //iOS 18 Only AppShortcut(intent: SearchSnippetIntent(), phrases: [ "Search \(.applicationName) Studio", "Search \(.applicationName)" ], shortTitle: "Search", systemImageName: "magnifyingglass") } let shortcutTileColor: ShortcutTileColor = .blue } The iOS 18 Only AppShortcut shows the following error but none of the options seem to work. Maybe I am going about it the wrong way. 'SearchSnippetIntent' is only available in iOS 18 or newer Add 'if #available' version check Add @available attribute to enclosing static property Add @available attribute to enclosing struct Thanks in advance for your help.

I use SoundAnalysis to analyze background sounds and have enabled background permissions. It worked well in previous iOS systems, but a warning appeared in the new iOS18beta version and sound analysis was stopped. Warning List: Execution of the command buffer was aborted due to an error during execution. Insufficient Permission (to submit GPU work from background) [Espresso::handle_ex_plan] exception=Espresso exception: "Generic error": Insufficient Permission (to submit GPU work from background) (00000006:kIOGPUCommandBufferCallbackErrorBackgroundExecutionNotPermitted); code=7 status=-1 Unable to compute the prediction using a neural network model. It can be an invalid input data or broken/unsupported model (error code: -1). CoreML prediction failed with Error Domain=com.apple.CoreML Code=0 "Failed to evaluate model 0 in pipeline" UserInfo={NSLocalizedDescription=Failed to evaluate model 0 in pipeline, NSUnderlyingError=0x30330e910 {Error Domain=com.apple.CoreML Code=0 "Failed to evaluate model 1 in pipeline" UserInfo={NSLocalizedDescription=Failed to evaluate model 1 in pipeline, NSUnderlyingError=0x303307840 {Error Domain=com.apple.CoreML Code=0 "Unable to compute the prediction using a neural network model. It can be an invalid input data or broken/unsupported model (error code: -1)." UserInfo={NSLocalizedDescription=Unable to compute the prediction using a neural network model. It can be an invalid input data or broken/unsupported model (error code: -1).}}}}}

Hello everyone, I am trying to train using CreateML Version 6.0 Beta (146.1), feature extractor Image Feature Print v2. I am using 100K images for a total ~4GB on my M3 Max 48GB (MacOs 15.0 Beta (24A5279h)) The images seems to be correctly read and visualized in the Data Source section (no images with corrupted data seems to be there). When I start the training it's all fine for the first 6k ~ 7k pictures, then I receive the following error: Failed to create CVPixelBufferPool. Width = 0, Height = 0, Format = 0x00000000 It is the first time I am using it, so I don't really have so much of experience. Could you help me to understand what could be the problem? Thanks a lot

We are experiencing a major issue with the native .version1 of the SoundAnalysis framework in iOS 18, which has led to all our user not having recordings. Our core feature relies heavily on sound analysis in the background, and it previously worked flawlessly in prior iOS versions. However, in the new iOS 18, sound analysis stops working in the background, triggering a critical warning. Details of the issue: We are using SoundAnalysis to analyze background sounds and have enabled the necessary background permissions. We are using the latest XCode A warning now appears, and sound analysis fails in the background. Below is the warning message we are encountering: Warning Message: Execution of the command buffer was aborted due to an error during execution. Insufficient Permission (to submit GPU work from background) [Espresso::handle_ex_plan] exception=Espresso exception: "Generic error": Insufficient Permission (to submit GPU work from background) (00000006:kIOGPUCommandBufferCallbackErrorBackgroundExecutionNotPermitted); code=7 status=-1 Unable to compute the prediction using a neural network model. It can be an invalid input data or broken/unsupported model (error code: -1). CoreML prediction failed with Error Domain=com.apple.CoreML Code=0 "Failed to evaluate model 0 in pipeline" UserInfo={NSLocalizedDescription=Failed to evaluate model 0 in pipeline, NSUnderlyingError=0x30330e910 {Error Domain=com.apple.CoreML Code=0 "Failed to evaluate model 1 in pipeline" UserInfo={NSLocalizedDescription=Failed to evaluate model 1 in pipeline, NSUnderlyingError=0x303307840 {Error Domain=com.apple.CoreML Code=0 "Unable to compute the prediction using a neural network model. It can be an invalid input data or broken/unsupported model (error code: -1)." UserInfo={NSLocalizedDescription=Unable to compute the prediction using a neural network model. It can be an invalid input data or broken/unsupported model (error code: -1).}}}}} We urgently need guidance or a fix for this, as our application’s main functionality is severely impacted by this background permission error. Please let us know the next steps or if this is a known issue with iOS 18.

Hi all, I'm tuning my app prediction speed with Core ML model. I watched and tried the methods in video: Improve Core ML integration with async prediction and Optimize your Core ML usage. I also use instruments to look what's the bottleneck that my prediction speed cannot be faster. Below is the instruments result with my app. its prediction duration is 10.29ms And below is performance report shows the average speed of prediction is 5.55ms, that is about half time of my app prediction! Below is part of my instruments records. I think the prediction should be considered quite frequent. Could it be faster? How to be the same prediction speed as performance report? The prediction speed on macbook Pro M2 is nearly the same as macbook Air M1!

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'm trying to use the Spatial model to perform Object Tracking on a .usdz file that I create. After loading the file, which I can view correctly in the console, I start the training. Initially, I notice that the disk usage on my PC increases. After several GB, the usage stops, but the training progress remains for hours at 0.00% with the message "About 8hr." How can I understand what the issue is? Has anyone else experienced the same problem? Thanks Diego

Hi, I found when continuously predicting with the same Core ML model in 120 FPS will be faster than in 60 FPS. I use Macbook Pro M2 and turn on ProMotion to run Core ML model prediction with a 120 FPS video, the average prediction time is 7.46ms as below: But when I turn off ProMotion, set 60 Hz refresh rate, and run Core ML model prediction with a 60 FPS video, the average prediction time is 10.91ms as below: What could be the technical explanation for these results? Is there any documentation or technical literature that addresses this behavior?

Hi I got access to developer beta 18.2 . All the features are working fine but image Playground stuck at Early Access requested. Can someone share how much time it takes before you are able to access image playground? I have been stuck for 3 hours

Hi Apple Developer Community, I’m exploring ways to fine-tune the SNSoundClassifier to allow users of my iOS app to personalize the model by adding custom sounds or adjusting predictions. While Apple’s WWDC session on sound classification explains how to train from scratch, I’m specifically interested in using SNSoundClassifier as the base model and building/fine-tuning on top of it. Here are a few questions I have: 1. Fine-Tuning on SNSoundClassifier: Is there a way to fine-tune this model programmatically through APIs? The manual approach using macOS, as shown in this documentation is clear, but how can it be done dynamically - within the app for users or in a cloud backend (AWS/iCloud)? Are there APIs or classes that support such on-device/cloud-based fine-tuning or incremental learning? If not directly, can the classifier’s embeddings be used to train a lightweight custom layer? Training is likely computationally intensive and drains too much on battery, doing it on cloud can be right way but need the right apis to get this done. A sample code will do good. 2. Recommended Approach for In-App Model Customization: If SNSoundClassifier doesn’t support fine-tuning, would transfer learning on models like MobileNetV2, YAMNet, OpenL3, or FastViT be more suitable? Given these models (SNSoundClassifier, MobileNetV2, YAMNet, OpenL3, FastViT), which one would be best for accuracy and performance/efficiency on iOS? I aim to maintain real-time performance without sacrificing battery life. Also it is important to see architecture retention and accuracy after conversion to CoreML model. 3. Cost-Effective Backend Setup for Training: Mac EC2 instances on AWS have a 24-hour minimum billing, which can become expensive for limited user requests. Are there better alternatives for deploying and training models on user request when s/he uploads files (training data)? 4. TensorFlow vs PyTorch: Between TensorFlow and PyTorch, which framework would you recommend for iOS Core ML integration? TensorFlow Lite offers mobile-optimized models, but I’m also curious about PyTorch’s performance when converted to Core ML. 5. Metrics: Metrics I have in mind while picking the model are these: Publisher, Accuracy, Fine-Tuning capability, Real-Time/Live use, Suitability of iPhone 16, Architectural retention after coreML conversion, Reasons for unsuitability, Recommended use case. Any insights or recommended approaches would be greatly appreciated. Thanks in advance!

I am working on adding indexing to my App Entities via IndexedEntity. I already, separately index my content via Spotlight. Watching 'What's New in App Intents', this is covered well but I have a question. Do I need to implement both CSSearchableItem's associateAppEntity AND also a custom implementation of attributeSet in my IndexedEntity conformance? It seems duplicative but I can't tell from the video if you're supposed to do both or just one or the other.

On the October 10/28 release day of Apple Intelligence I opted in. My iPhone and iPad immediately went to "waitlist" and within 2 to 3 hours were ready to initialize Apple Intelligence. My MacBook Pro 14" with M3 Pro processor and 18 GB or RAM has been stuck on "preparing" since release day (6 days now). I've tried numerous workarounds that I found on forums as well as talking to Apple support, who basically had me repeat the workarounds that I found on forums. I've tried changing region to an area that does not have Apple Intelligence and then back to the US, I've changed Siri language to an unsupported one and back to a supported one, and I have tried disabling background/startup Apps, I've disabled and reenabled Siri. Oh, I've restarted a bunch and let the Mac alone for hours at a time. I've noticed that my selected Siri voice seems to not download. Finally, after several chats and calls with Apple support, I was told that it's Beta software, they can't help me, and I should try the developer forums.... so here I am. Any advice?