Running TFLite Inference Offline

[volome]

Search before asking

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

Question

If I train a model and need to convert it to say TFlite and use it on my embedded hardware that has no internet connection and just my own app. Can I do that and is that an extra cost.

Additional

This is not very clear in your movie, you always refer using our app.

[github-actions]

👋 Hello @volome, 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]

@volome hello!

Thank you for reaching out with your question. Yes, you can train a model and convert it to TFLite for use on your embedded hardware without an internet connection. There is no extra cost associated with converting your model to TFLite and deploying it on your hardware for offline use. The AGPL-3.0 license allows for such use cases, provided you comply with the terms of the license.

For detailed guidance on the conversion process, please refer to the Ultralytics HUB Docs. If you have any further questions or need assistance, feel free to ask. We're here to help!

[volome]

Thank you for your response! Super very helpful

…

On Mon, 8 Jan 2024 at 14:15, Ultralytics AI Assistant < ***@***.***> wrote: @volome <https://github.com/volome> hello! Thank you for reaching out with your question. Yes, you can train a model and convert it to TFLite for use on your embedded hardware without an internet connection. There is no extra cost associated with converting your model to TFLite and deploying it on your hardware for offline use. The AGPL-3.0 license allows for such use cases, provided you comply with the terms of the license. For detailed guidance on the conversion process, please refer to the Ultralytics HUB Docs. If you have any further questions or need assistance, feel free to ask. We're here to help! — Reply to this email directly, view it on GitHub <#524 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAAWEYO735FV4ROIV3UBL23YNPWQXAVCNFSM6AAAAABBQ7URO2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTQOBQHE4DONRVGU> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[UltralyticsAssistant]

You're very welcome, @volome! I'm glad I could assist you. 😊 If you have any more questions in the future or need further support, don't hesitate to reach out. Good luck with your project, and have a great time working with your model on your embedded hardware!