How to use the output of a model converted to CoreML?

[Joao-Neves]

Search before asking

• I have searched the HUB issues and discussions and found no similar questions.

Question

Hello, I've trained a YOLOv8x model in the Hub and then converted it to CoreML.

When adding the CoreML model to Xcode it tells me that the output is a var_1365 that is a MultiArray : Float32 1 × 5 × 8400 array.
I was expecting a list of boxes or something similar.

How do I use the var_1365? Do I need to convert it to something else?

Thank you for your help 🙇.

Additional

No response

[github-actions]

👋 Hello @Joao-Neves, thank you for raising an issue about Ultralytics HUB 🚀! Please visit our HUB Docs to learn more:

• Quickstart. Start training and deploying YOLO models with HUB in seconds.
• Datasets: Preparing and Uploading. Learn how to prepare and upload your datasets to HUB in YOLO format.
• Projects: Creating and Managing. Group your models into projects for improved organization.
• Models: Training and Exporting. Train YOLOv5 and YOLOv8 models on your custom datasets and export them to various formats for deployment.
• Integrations. Explore different integration options for your trained models, such as TensorFlow, ONNX, OpenVINO, CoreML, and PaddlePaddle.
• Ultralytics HUB App. Learn about the Ultralytics App for iOS and Android, which allows you to run models directly on your mobile device.
  • iOS. Learn about YOLO CoreML models accelerated on Apple's Neural Engine on iPhones and iPads.
  • Android. Explore TFLite acceleration on mobile devices.
• Inference API. Understand how to use the Inference API for running your trained models in the cloud to generate predictions.

If this is a 🐛 Bug Report, please provide screenshots and steps to reproduce your problem to help us get started working on a fix.

If this is a ❓ Question, please provide as much information as possible, including dataset, model, environment details etc. so that we might provide the most helpful response.

We try to respond to all issues as promptly as possible. Thank you for your patience!

[glenn-jocher]

@Joao-Neves if you are using CoreML exports you probably want to set NMS=True, which will process all detections and only return actual objects seen. Then you can use Xcode to preview inference results etc.

[Joao-Neves]

@glenn-jocher thank you so much ❤️! That was it! I can get data I can work with now 😁!

[UltralyticsAssistant]

I'm really glad to hear that your issue is resolved, @Joao-Neves! It's delightful to know that the solution worked for you. Remember, the successful application of your model is a testament to your hard work.

Moreover, the strides we make here are the culmination of the combined efforts of the YOLO and Ultralytics communities. If you have more questions or face any other issues in the future, don't hesitate to ask. Happy coding!