option to change training mid training from collab to private agent, resume and change setup from gpu to cpu

[Omer1004]

Search before asking

• I have searched the HUB issues and found no similar feature requests.

Description

option to change training mid training from collab to private agent, resume and change setup from gpu to cpu

Use case

add option in the hub to change from gpu training to cpu training on private agent so that I can resume the training on another device and flags like device='mps' and resume=True doesnt work when working with the hub

Additional

No response

[github-actions]

👋 Hello @Omer1004, 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!

[UltralyticsAssistant]

@Omer1004 hello! Thank you for bringing up this feature request. 🌟

Currently, the ability to switch training environments (from Colab to a private agent) or hardware (from GPU to CPU) mid-training and resuming seamlessly is not directly supported through the Ultralytics HUB interface. This involves complex state management and hardware compatibility considerations, especially when transitioning between different types of devices and environments.

However, we understand the flexibility this feature could offer and the potential benefits for users who need to adapt their training workflows due to various constraints. We'll take this suggestion into our planning discussions for future updates. Your input is invaluable in helping us improve.

For now, to manage training across different environments or hardware, you might need to manually stop your training, download your latest checkpoint, and restart the training on the new setup by specifying the checkpoint. Please refer to our documentation at https://docs.ultralytics.com/hub for guidance on managing training sessions and checkpoints.

We appreciate your contribution to the discussion and your interest in making the Ultralytics HUB more versatile! Keep the suggestions coming. 🚀

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐