Using Ultralytics SAHI Tiled Inference in Ultralytics Hub

[Sabeeh-H]

Search before asking

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

Question

I would like to use SAHI in order to process large images with smaller objects in Ultralytics Hub. However, I could not find any place to use it prior to deployment, is there any way I can call the function in Hub, or do I have to use a virtual machine for it instead?

Additional

No response

[github-actions]

👋 Hello @Sabeeh-H, 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!

[pderrenger]

Hello! 😊 We're glad you're interested in using SAHI for tiled inference with large images in Ultralytics HUB. Currently, the HUB doesn't directly support the SAHI utility within its user interface or API for preprocessing large images before deployment.

For now, you'd need to process your images using SAHI locally or in a virtual machine environment before uploading the processed images or deploying models in the HUB. This step involves using SAHI to slice your large images into smaller, manageable tiles, perform inference on each tile, and then merge the results.

For detailed instructions on how to use SAHI with YOLO models, including slicing and merging strategies, please refer to the official SAHI documentation and examples. Remember, after processing your images with SAHI, you can easily upload and manage your models or inference results directly in the Ultralytics HUB.

If you have further questions or need assistance with other features in the HUB, feel free to reach out. Happy detecting!