Choosing Yolov8 OBB model when selecting model to train with

[Drake-Sunryder]

Search before asking

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

Question

Apologies if I somehow missed where this is explained or addressed somewhere, but I couldn't find anything. I see that when you upload your own dataset to the Hub, you have the option of choosing to specify that it's an OBB dataset.

My understanding, based on the explanations that I've seen on training OBB models is that they require specific models such as YOLOv8n-obb or YOLOv8x-obb. However, in the second step of training a model when you pick from a list of models, such OBB models are nowhere to be found. Is this intentional or am I missing something and/or misunderstanding something?

How exactly to I train a dataset with a YOLOv8 OBB model in the Ultralytics Hub?

Additional

No response

[github-actions[bot]]

👋 Hello @Drake-Sunryder, 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!

[sergiuwaxmann]

Hello @Drake-Sunryder!

In order to have access to OBB architectures, you need to select an OBB dataset in the first step.

You can make sure you selected an OBB dataset by training a model directly from the dataset page of your OBB dataset.

You can try this using our Ultralytics DOTA8 Dataset - read more about uploading a dataset here.

[Drake-Sunryder]

Hello @Drake-Sunryder!

In order to have access to OBB architectures, you need to select an OBB dataset in the first step.

You can make sure you selected an OBB dataset by training a model directly from the dataset page of your OBB dataset.

You can try this using our Ultralytics DOTA8 Dataset - read more about uploading a dataset here.

Yup, after double-checking the dataset I uploaded, I didn't upload it as an OBB dataset correctly. This one's on me! Thanks for the help, though!

[sergiuwaxmann]

@Drake-Sunryder No worries!