[tags:wwdc20-10087]

Hello, When trying to load my CoreML model which is encrypted, I am getting: Error loading model: Error Domain=com.apple.CoreML Code=9 Operation not supported on this platform. UserInfo={NSLocalizedDescription=Operation not supported on this platform.}. When using the simulator. Can this only be tested on an actual device? Thank you, Andres

I was able to access the downloaded collection and the models inside it. But after deleting the app and re-installing, i get empty model collection on calling beginAccessing(identifier:completionHandler:) method. There is no deployment id associated with the downloaded collection, thus no models inside the collection. Is there a way to delete the older collection in file system and force download the model from the cloud ? Any help would be greatly appreciated. Thanks.

After my model was deployed to the cloud, I successfully downloaded the model collection through the beginAccessingModelCollectionWithIdentifier:completionHandler: API for the first time. Then I delete the app, install and fetch again, it will fail to download with timeout error.

am very new to CoreMl and I want to retrieve a model from Coreml model deployment which was released this year at WWDC. I made an app that just classifies special and rare things and I uploaded that model.archive to the CoreMl Model deployment dashboard. I successfully deployed the model and its showing as active. now the problem is I am unable to retrieve that model, I have tried a lot, I even saw all the WWDC sessions on that one and even copied that code from that session but all in vain. Here is my whole model loading and retrieving code my classification code which takes an image and does all the loading of CoreML and from CoreML model deployment. func updateClassifications(for image: UIImage) { ttttclassificationLabel.text = Classifying... tttt ttttvar models = try? VNCoreMLModel(for: SqueezeNet().model) tttt ttttif let modelsss = models { ttttttextensionofhandler(ciimage: image, vnmodel: modelsss) ttttttreturn tttt} tttt tttt_ = MLModelCollection.beginAccessing(identifier: TestingResnetModel) { [self]

Hi all, I have a problem with retrieving a model collection from a deployment. I tried to implement it like it was shown in WWDC 'Use model deployment and security with Core ML - https://developer.apple.com/videos/play/wwdc2020/10152/' session and here - https://developer.apple.com/forums/thread/650464?answerId=614845022#614845022 but I found that beginAccesing method doesn't exist for MLModelCollection class. Then I used Apple's documentation for 'Retrieving a Model Collection from a Deployment - https://developer.apple.com/documentation/coreml/core_ml_api/retrieving_a_model_collection_from_a_deployment' and implement it like it is described, but status property of the collection model is always MLModelCollection.Status.syncing. Code: let coinModelCollection = MLModelCollection(identifier: TestCoinDetector) coinModelCollection.isSynchronizationEnabled = true print(Model collection status (coinModelCollection.status.rawValue)) if let coinModel = coinModelCollection.entries?[CoinDetector] { // entries are alwa

HI, I have archived CoreML model and deployed it in CoreML Model deployment site. If I try to access it in app, facing issue like Failed to begin access for model collection with identifier. I have double checked the identifiers in my app and CoreML model deployment, both are same. Not sure what mistake I'm making, Thanks in advance. func asddasd() { if #available(iOS 14.0, *) { let progress = MLModelCollection.beginAccessing(identifier: MainCoreMLCollection, completionHandler: modelCollectionAvailable) debugPrint(progress) } else { // Fallback on earlier versions } } @available(iOS 14.0, *) func modelCollectionAvailable(result: Result) { switch result { case .success(let collection): debugPrint(Model collection (collection.identifier) is now available.) // Load a model from the collection. loadModel(BCGSearchClassifier, from: collection) case .failure(let error): debugPrint(Error accessing a model collection: (error)) } } @available(iOS 14.0, *) func loadModel(_ modelName: String, from collection: MLModelCol

I have been trying to implement the coreML distribution example from wwdc but I keep getting the following errors: 2020-07-23 08:25:01.436746+0200 AppleCloudModelDistribution[9173:2724329] [coreml] Could not create team identifier error=(null) 2020-07-23 08:25:01.436904+0200 AppleCloudModelDistribution[9173:2724329] [coreml] MLModelCollection: unable to extract team identifier for the client. error:(null) 2020-07-23 08:25:01.493894+0200 AppleCloudModelDistribution[9173:2724329] [coreml] MLModelCollection: namespace (xxxx) registration failed. Error Domain=TRIGeneralErrorDomain Code=3 Unable to determine teamId for calling process. UserInfo={NSLocalizedDescription=Unable to determine teamId for calling process.} let _ = MLModelCollection.beginAccessing(identifier: xxxx) { (result) in var modelURL: URL? switch result { case let .success(collection): modelURL = collection.entries[xxxx]?.modelURL case let .failure(error): print(error.localizedDescription) print(Couldn't load model from cloud) } let result = loadC

Hello i have a problem with uploading a model (243 MB) to a model collection when i do the same for my other collections where the models is smaller its works. But with this model of 243 MB is does not work and end up not creating a deployment on the collection. I am not sure if there is a limit on size or some other problem? if anyone have an ideer about what i can try to get my model uploaded.

i have learn the vedio of WWDC2020. i use the objectC method :beginAccessingModelCollectionWithIdentifier:completionHandler: to retrieve the archive file from the dashboard . where i recrive the wrong message: [coreml] MLModelCollection: namespace (87HGLU5YX9.DeploymentModelCollection) download failed. Error Domain=com.apple.trial Code=0 Unknown error. UserInfo={NSLocalizedDescription=Unknown error.} the second time i running the app, i got the wrong message: [coreml] MLModelCollection: experimentId unexpectedly not returned device: iphone7 ios14.0.1 xcode: Version 12.0.1 (12A7300) ios deployment target 14.0 can you help me? thanks.

I tried out the CoreML Model Encryption feature that comes with Xcode 12. I generated the key - https://developer.apple.com/documentation/coreml/core_ml_api/generating_a_model_encryption_key and added the --encrypt compiler flag - https://developer.apple.com/documentation/coreml/core_ml_api/encrypting_a_model_in_your_app as described in the docs. Everything works on iOS 14. However on an iOS 13 simulator I get a runtime error saying MLModelAsset: load failed with error Error Domain=com.apple.CoreML Code=3 No known class for loading model type INVALID UserInfo={NSLocalizedDescription=No known class for loading model type INVALID} So iOS 13 can't handle the encrypted model and says it's invalid, which makes sense I guess. But how are we supposed to maintain backwards-compatibility to iOS 13? (As expected the error goes away if I remove the --encrypt compiler flag again.) I want to add that I did NOT use the new async API - https://developer.apple.com/documentation/coreml/mlmodel/3600218-load to load the model,

In the session Use model deployment and security with Core ML, I know that Apple provide cloud deploy CoreML models and model encryption, but they are separated. Can I encrypt the model and use cloud to deploy that encryped model. Or did cloud deployment already do the encryption automatically?

Can one perform model inference on the model deployment page? Or is this just a step in the deployment process to the device? Next, does this model storage count towards any of the various storage quotas? Does the encrypted ML model get decrypted every time it needs to perform an inference operation on device? Just curious about what's actually is happening on the user's device here. Finally, is this model deployment process the same for macOS 11?

I have a custom Core ML model built with Keras that has a couple of updatable layers. I was wondering if I switched this model to be deployed from the cloud rather than packaged with the app, would the on-device personalized changes transfer whenever I deploy a model over the cloud or would a user have to start with a fresh, new model every time? Similarly, do on-device personalized models work with model encryption? Thanks!

It would be amazing if targeted deployment could be even more granular or requested on-demand. For instance, being able to download an ML model tailored to a certain location being visited would be very powerful. Any chance of that being in the pipe-line or better yet, is there a way to do that already?

Excellent talk on model deployment, encryption. Given some users experience network issues, for encrypted models within the app how could the key be downloaded as close to app download/install time as possible? e.g. the user has network access when they install the app, so if the key for the model could be downloaded at install time and stored securely locally rather than at model load time that could give a better experience.