Explore the power of machine learning and Apple Intelligence within apps. Discuss integrating features, share best practices, and explore the possibilities for your app here.

All subtopics

Post

Replies

Boosts

Views

Activity

Apple Intelligence / Mac Mail : Summaries Unavailable
At one point, Mac Mail's apple added a summarize functionality that worked. Now when I click on Summarize, I get: "Summaries Unavailable Mail summarization is unavailable at this time. Try again later." I've rebooted, stopped/restarted Apple AI, waited a day to see if it was synching up things, etc. I'm running the latest version of Apple OS (Version 15.1 (24B82)). any ideas?
2
0
233
3w
Playground (early access)
Is it just me or is early access image playground not available, been waiting for a little over 24hrs and still no access. (no rush for the team if there’s smth wrong) they might be busy rolling out the first few apple intelligence features (ios 18.1) public release.
4
2
1.3k
3w
Max 16k images for Image Classifier training????
I'm hitting a limit when trying to train an Image Classifier. It's at about 16k images (in line with the error info) - and it gives the error: IOSurface creation failed: e00002be parentID: 00000000 properties: { IOSurfaceAllocSize = 529984; IOSurfaceBytesPerElement = 4; IOSurfaceBytesPerRow = 1472; IOSurfaceElementHeight = 1; IOSurfaceElementWidth = 1; IOSurfaceHeight = 360; IOSurfaceName = CoreVideo; IOSurfaceOffset = 0; IOSurfacePixelFormat = 1111970369; IOSurfacePlaneComponentBitDepths = ( 8, 8, 8, 8 ); IOSurfacePlaneComponentNames = ( 4, 3, 2, 1 ); IOSurfacePlaneComponentRanges = ( 1, 1, 1, 1 ); IOSurfacePurgeWhenNotInUse = 1; IOSurfaceSubsampling = 1; IOSurfaceWidth = 360; } (likely per client IOSurface limit of 16384 reached) I feel like I was able to use more images than this before upgrading to Sonoma - but I don't have the receipts.... Is there a way around this? I have oodles of spare memory on my machine - it's using about 16gb of 64 when it crashes... code to create the model is let parameters = MLImageClassifier.ModelParameters(validation: .dataSource(validationDataSource), maxIterations: 25, augmentation: [], algorithm: .transferLearning( featureExtractor: .scenePrint(revision: 2), classifier: .logisticRegressor )) let model = try MLImageClassifier(trainingData: .labeledDirectories(at: trainingDir.url), parameters: parameters) I have also tried the same training source in CreateML, it runs through 'extracting features', and crashes at about 16k images processed. Thank you
1
0
158
3w
switching region from China to US, Apple Intelligence still unable to use
Originally when Apple Intelligence launched there are some T&C for using and activate this Apple Intelligence. For activating Apple Intelligence at China first of all purchased iPhone must be non-Chinese iPhone means that the iPhone aren’t purchased in China not include Hong Kong and Macau. Also if use this Chinese Apple account are also unable to activate the Apple Intelligence. To activate the Apple Intelligence, I have travel to Hong Kong and purchase iPhone 16 pro Max. To reach the requirement of activating Apple Intelligence, I’ve decided to switch my region from China to United States. I’ve started to switch my account from October 19, CST 2:00am, Shanghai time 3:00pm. Till now CST time 8:30am October 24, Shanghai Time 9:30pm I still can’t join the Apple Intelligence waitlist. I’m also upgraded my phone to iOS 18.2. I’ve contacted the Apple support using my Chinese phone number and it transferred to me Philippines Apple support team. It seems like the Philippine Apple support team doesn’t help me get anything. The Philippine Apple support team keeps saying that the beta version iOS right now in my phone has some problem on it. But when I log out this Apple ID, and changed to another Apple ID that is UK ones. I can successfully enable the Apple Intelligence. What does this say?! This shows that my Apple account has a problem on it. It doesn’t switch successfully to United States server! And the Philippine Apple support team keep asking me to restore my iPhone like crazy! I’ve told them that I have used several Apple account that is from United States and United Kingdom that can successfully enable the Apple Intelligence. But the Philippine Apple support team said that my Apple account doesn’t have any problem! Apple please solve the problem! Anyone who have facing this kind of problem please share to us!!! Cheers!
1
0
707
3w
Core ML Model Prediction in 120 FPS faster than 60 FPS
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?
1
0
186
3w
New Vison api - CoreML - "The VNDetectorProcessOption_ScenePrints required option was not found"
I'm trying to run a coreML model. This is an image classifier generated using: let parameters = MLImageClassifier.ModelParameters(validation: .dataSource(validationDataSource), maxIterations: 25, augmentation: [], algorithm: .transferLearning( featureExtractor: .scenePrint(revision: 2), classifier: .logisticRegressor )) let model = try MLImageClassifier(trainingData: .labeledDirectories(at: trainingDir.url), parameters: parameters) I'm trying to run it with the new async Vision api let model = try MLModel(contentsOf: modelUrl) guard let modelContainer = try? CoreMLModelContainer(model: model) else { fatalError("The model is missing") } let request = CoreMLRequest(model: modelContainer) let image = NSImage(named:"testImage")! let cgImage = image.toCGImage()! let handler = ImageRequestHandler(cgImage) do { let results = try await handler.perform(request) print(results) } catch { print("Failed: \(error)") } This gives me Failed: internalError("Error Domain=com.apple.Vision Code=7 "The VNDetectorProcessOption_ScenePrints required option was not found" UserInfo={NSLocalizedDescription=The VNDetectorProcessOption_ScenePrints required option was not found}") Please help! Am I missing something?
1
0
210
3w
Apple Intelligence missing Image features released in 18.2 today
I'm using an iPhone 15 Pro Max and running developer beta 18.2 released today. I've already been an 'Apple Intelligence' user and now have been able to link it with my PAID ChatGPT account. HOWEVER; I'm searching for these Image features everyone seems to be posting about and cannot find them anywhere. I'm apparently supposed to sign up for beta access to the Image features through some new Apple natively released app that was supposedly included in this build update, which I cannot find. What gives??!!
4
2
729
3w
Question about Apple Intelligence
I downloaded the RC beta version on my Macbook and joined the waitlist so far I haven't received any message or any kind of notifications that I'm in but I have a question kinda silly but just want confirmation. By joining the beta and AI on my MacBook, whenever the official version is released, am I gonna have AI on my iPhone since already joined AI through my MacBook in the beta version? Kinda curious about it.
1
0
155
4w
Keras 3 and Tensorflow GPU does not have support on apple silicon
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
2
0
319
4w
Apple intelligence is not available in the iPhone 15 Pro brought from China.
My iPhone 15 Pro is from Hong Kong (China). I am outside of China and Asia in general. I have never been to China myself and the iPhone was activated in another country. And it is not the EU. My iPhone's language, Siri and region settings are changed to US English. Updated to iOS 18.1 RC. But Apple Intelligence doesn't show up in the Siri settings.
1
1
274
4w