Dual GPU training cannot be set up inside the HUB.

[LeonYWang]

Search before asking

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

Question

Dual GPU training cannot be set up inside the HUB. "Advanced Model Configuration" Device to run on. When set to GPU, CUDA device 0 is utilized by default (if available). I need to modify it to CUDA device 0,1

Additional

No response

[UltralyticsAssistant]

👋 Hello @LeonYWang, 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.
  • For advanced setup details (e.g., multi-GPU training), check the model configuration options and documentation for deeper insights.
• 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.

To assist us in addressing 🐛 bugs or ❓ questions swiftly, please include any additional details that might help clarify the issue. Specifically for this case:

1. Can you provide more details about your environment setup (e.g., GPU specs, CUDA version, environment configurations)?
2. If this involves a misconfiguration, can you share any screenshots or error logs?
3. For advanced training like multi-GPU use, are there any additional steps you've attempted that we should know about?

Additionally, please check out our Minimum Reproducible Example (MRE) guide to ensure your report includes all necessary details for troubleshooting 🔍.

This is an automated response to help guide you 😊. An Ultralytics engineer will also review your issue and provide further assistance soon. Thank you for your patience and for helping improve Ultralytics HUB! 🚀

[sergiuwaxmann]

@LeonYWang Hello!
In the Advanced Model Configuration, use the Custom field. You can select the device option there and type 0,1 (no space).