944 questions
0
votes
1
answer
51
views
How to accurately map 2D Vision bounding boxes (CoreML) to 3D world coordinates using ARKit Raycast during a RoomPlan session?
I am building an iOS 17 application that integrates Apple's RoomPlan (RoomCaptureSession) with a custom Edge AI model (YOLOv8 via CoreML and Vision framework) to detect structural defects (like cracks)...
- 1
1
vote
0
answers
90
views
How to get pass `wgpu::Buffers` to `CoreML` `predict` as inputs
I am have a wgpu::Buffer. I am trying to create input to a CoreML from this buffer.
let hal_buffer = unsafe { buffer.as_hal::<wgpu::hal::metal::Api>() };
let Some(hal_buffer) = ...
- 117
0
votes
0
answers
78
views
Compilation error logged but prediction seems to work without errors
I'm about to integrate CoreML based inference using the Objective-C CoreML API in a C++ based macOS application that used Onnxruntime until now. It all seems to work fine and I the performance has ...
- 2,030
0
votes
0
answers
57
views
CoreML Model not working as expected in SwiftUI iOS App
I´m using an ML model that was created with CreateML 6.1. In the CreateML Preview section, it works as expected. The model is exported and opened in Xcode 16.2. For testings purposes, I'm using the ...
- 63
0
votes
0
answers
96
views
How to implement a CoreML model into an iOS app properly?
I am working on a lung cancer scanning app for iOS with a CoreML model and when I test my app on a physical device, the model results in the same prediction 100% of the time. I even changed the names ...
- 11
1
vote
0
answers
204
views
CoreML model error happening in code. I need help troubleshooting this error resulting in my xcode app
I have been getting the following error messages on my Xcode App:
E5RT: Espresso exception: "Invalid state": MpsGraph backend validation on incompatible OS (11)
[Espresso::handle_ex_] ...
- 11
0
votes
0
answers
70
views
CreateML model performing completely differently on macOS vs iPadOS
I have trained a face sentiment CoreML model using CreateML's app. When using the live preview in the CreateML's app I get a model that roughly works (i.e changes in facial expression results in ...
- 628
2
votes
0
answers
189
views
How to use a self trained YOLO OBB model in Xcode without multiarray output
I'm new to Xcode and have some trouble getting my model into an appropriate format.
I have quite a similar problem as in this unanswered
question but for OBBs:
I trained a YOLOv8n-obb model on a ...
- 21
-1
votes
1
answer
207
views
Failed to read model package AND Error: A valid manifest does not exist at path | CoreML Model does not get loaded in Xcode
The idea was to create a simple image picker on iOS. Once the image is loaded, the app shall output its analysis with %.
Right now the CoreML model will not be loaded and crashes with:
...
- 41
-1
votes
1
answer
286
views
How to Add .mlmodel File to Xcode App Playgrounds (.swiftpm) Project?
I’m working on an Xcode App Playground project (.swiftpm) and trying to add a .mlmodel file (e.g., Exercises.mlmodel) to it. However, when I add the .mlmodel file to my project, I encounter the ...
- 337
2
votes
1
answer
208
views
Use YOLO with unbounded input exported to an mlpackage/mlmodel file
I want to create an .mlpackage or .mlmodel file which I can import in Xcode to do image segmentation. For this, I want to use the segmentation package within YOLO to check out if it fit my needs.
The ...
- 13.6k
-1
votes
1
answer
75
views
iOS Swift dynamic Machine Learning from user data
is it possible to use apple ML framework to dynamically learn from users behaviour in the app? I've trained a model using Create ML application, can I then update and retrain from the iOS device? This ...
- 162
1
vote
0
answers
286
views
Crash inside of Vision framework during VNImageRequestHandler use
I've been dealing with a puzzling issue for some time now, and I’m hoping someone here might have insights or suggestions.
The Problem: We’re observing an occasional crash in our app that seems to ...
- 1,040
0
votes
0
answers
57
views
Core ML prediction for Image Classification Create ml model predict same result for different images
I am exploring the Apple Core ML framework.
I created a training model using Create ML app. Image Classification to identify the image is cat or a dog. The data set I used is referred from
https://www....
- 11.3k
0
votes
0
answers
50
views
How to convert pytorch segmentation to CoreML
The script gets the DeepLabV3 + MobileNet model from the pytorch.
It then saves it to .pt which can be opened in Netron.
It then converts it to .mlpackage which cannot be opened in Netron - it gives ...
- 53