Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

tflite #13375

Open
1 of 2 tasks
motesz opened this issue Oct 23, 2024 · 2 comments
Open
1 of 2 tasks

tflite #13375

motesz opened this issue Oct 23, 2024 · 2 comments
Labels
enhancement New feature or request question Further information is requested

Comments

@motesz
Copy link

motesz commented Oct 23, 2024

Search before asking

  • I have searched the YOLOv5 issues and found no similar feature requests.

Description

how can i export yolov5s into tflite

Use case

No response

Additional

No response

Are you willing to submit a PR?

  • Yes I'd like to help by submitting a PR!
@motesz motesz added the enhancement New feature or request label Oct 23, 2024
@UltralyticsAssistant UltralyticsAssistant added the question Further information is requested label Oct 23, 2024
@UltralyticsAssistant
Copy link
Member

👋 Hello @motesz, thank you for your interest in YOLOv5 🚀! It looks like you're looking for guidance on exporting YOLOv5s to TFLite. Please check out our ⭐️ Tutorials for comprehensive guides, including converting models to different formats like TFLite.

If this is a 🐛 Bug Report related to TFLite, please provide a minimum reproducible example so we can better assist you.

For general export instructions, ensure your environment meets the necessary requirements:

Requirements

Python>=3.8.0 with all requirements.txt dependencies installed, including PyTorch>=1.8. To set up your environment:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Exporting to TFLite

YOLOv5 includes scripts for exporting models to various formats. You can find export scripts in the repository:

python export.py --weights yolov5s.pt --include tflite  # export to tflite

Make sure you have the required dependencies for exporting to TFLite. You can find specific instructions in our repository documentation.

Status

YOLOv5 CI

If the CI badge is green, all tests are passing, indicating that the current YOLOv5 functionalities are working as expected in various environments including macOS, Windows, and Ubuntu.

This is an automated response, but an Ultralytics engineer will also assist you soon. If you have other questions, feel free to reach out! 😊

P.S. Explore our latest models like YOLOv8 for enhanced performance and features!

@pderrenger
Copy link
Member

@motesz to export YOLOv5s to TFLite, use the command: python export.py --weights yolov5s.pt --include tflite. Ensure you have installed all dependencies from requirements.txt. For more details, refer to the model export guide.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants